INDEX

Explanations

words related to objects or actions involving rubber

oai_token-act-pair · gpt-3.5-turbo

references to rubber and its various applications or connotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

erest

-0.84

emi

-0.81

orld

-0.80

arios

-0.76

rophe

-0.75

ulhu

-0.73

places

-0.73

erers

-0.72

erer

-0.72

erent

-0.71

POSITIVE LOGITS

ized

0.97

 latex

0.97

neck

0.95

 tubing

0.88

 bands

0.87

band

0.86

 rubber

0.85

 gloves

0.84

 ding

0.82

 band

0.82

Activations Density 0.016%

words related to objects or actions involving rubber

references to rubber and its various applications or connotations

No Comments

No Known Activations