INDEX

Explanations

dates expressed as months and years

oai_token-act-pair · gpt-3.5-turbo

unique characters or symbols in different languages or formats

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

xual

-0.60

feature

-0.52

 tremend

-0.51

 hunger

-0.50

undown

-0.48

Nad

-0.48

Ö¼

-0.48

ensical

-0.48

iane

-0.48

 genders

-0.48

POSITIVE LOGITS

steamapps

0.62

ombo

0.59

utra

0.56

ornia

0.55

ibal

0.54

wagen

0.52

dq

0.52

asionally

0.51

itent

0.51

chuk

0.51

Activations Density 1.206%

dates expressed as months and years

unique characters or symbols in different languages or formats

No Comments

No Known Activations