INDEX

Explanations

phrases related to challenging or potentially negative situations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating challenges or difficulties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Cosponsors

-0.70

 successors

-0.60

 surprised

-0.59

udos

-0.56

bnb

-0.56

ADS

-0.55

 Wildlife

-0.54

iens

-0.54

ccording

-0.54

ADRA

-0.54

POSITIVE LOGITS

 theirs

0.89

 hers

0.75

existent

0.71

tight

0.66

 inex

0.65

itored

0.64

limits

0.63

itized

0.62

ogged

0.61

ranged

0.61

Activations Density 0.776%

phrases related to challenging or potentially negative situations

phrases indicating challenges or difficulties

No Comments

No Known Activations