INDEX

Explanations

words related to physical tools or actions involving force

oai_token-act-pair · gpt-3.5-turbo

terms related to tools and mechanical actions that disrupt or interfere

oai_token-act-pair · gpt-4o-mini Triggered by @bot

words related to tools or actions that imply alteration or repair, particularly focusing on the root 'wrench'

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cation

-0.90

itative

-0.80

vertis

-0.78

cious

-0.74

itÃ©

-0.73

ombat

-0.73

phis

-0.72

veland

-0.71

anyon

-0.71

yrics

-0.71

POSITIVE LOGITS

 wrench

1.17

 Schr

1.12

 bitters

0.81

 levers

0.71

 fraught

0.71

 pinch

0.71

 wedge

0.70

 scissors

0.70

driver

0.68

 Sawyer

0.66

Activations Density 0.028%

words related to physical tools or actions involving force

terms related to tools and mechanical actions that disrupt or interfere

words related to tools or actions that imply alteration or repair, particularly focusing on the root 'wrench'

No Comments

No Known Activations