INDEX

Explanations

verbs related to movement or actions involving physical contact

oai_token-act-pair · gpt-3.5-turbo

actions related to movement and expressions of joy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

mel

-0.83

nery

-0.82

cms

-0.79

si

-0.79

xy

-0.79

yon

-0.77

chin

-0.77

xus

-0.76

bal

-0.75

pps

-0.74

POSITIVE LOGITS

 bananas

0.82

GGGGGGGG

0.78

 exha

0.76

 behavi

0.73

 Squid

0.72

 elbows

0.71

 uphill

0.71

 ducks

0.70

 Lizard

0.69

 turtle

0.68

Activations Density 0.179%

verbs related to movement or actions involving physical contact

actions related to movement and expressions of joy

No Comments

No Known Activations