INDEX

Explanations

adjectives expressing doubt or uncertainty

oai_token-act-pair · gpt-3.5-turbo

terms that indicate skepticism or doubt regarding credibility

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

olon

-0.94

ften

-0.80

brate

-0.80

ummer

-0.79

xual

-0.76

OVA

-0.73

agos

-0.72

berman

-0.71

brates

-0.71

learning

-0.70

POSITIVE LOGITS

 legality

0.91

 questionable

0.82

 dubious

0.80

necess

0.76

gery

0.73

 suspic

0.72

 sounding

0.69

 witchcraft

0.68

 proposition

0.68

 motives

0.68

Activations Density 0.019%

adjectives expressing doubt or uncertainty

terms that indicate skepticism or doubt regarding credibility

No Comments

No Known Activations