INDEX

Explanations

words related to striking or hitting something forcefully

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "strikes" in various contexts, particularly those linked to sports or actions

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

ħĭ

-0.86

regon

-0.82

ŀ

-0.75

adian

-0.75

anson

-0.73

raints

-0.72

umption

-0.68

ophers

-0.67

etsk

-0.65

opher

-0.65

POSITIVE LOGITS

breakers

0.93

force

0.91

 strike

0.89

out

0.89

ters

0.81

 strikes

0.81

outs

0.79

strike

0.78

 force

0.78

ting

0.77

Activations Density 0.018%

words related to striking or hitting something forcefully

terms related to the concept of "strikes" in various contexts, particularly those linked to sports or actions

No Comments

No Known Activations