INDEX

Explanations

names of political figures, organizations, and events

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

proper nouns related to news and political figures

oai_token-act-pair · gpt-3.5-turbo

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

)--

-0.56

''.

-0.55

 ......

-0.54

.''

-0.53

 ....

-0.53

utterstock

-0.53

}.

-0.51

)?

-0.51

Miami

-0.51

....

-0.50

POSITIVE LOGITS

seless

0.59

atism

0.51

osite

0.47

"#

0.46

uin

0.46

nered

0.46

 hotline

0.46

cheat

0.46

TextColor

0.46

acial

0.46

Activations Density 1.232%

names of political figures, organizations, and events

proper nouns related to news and political figures

No Comments

No Known Activations