INDEX

Explanations

phrases containing the prefix "non-" followed by a hyphen and a word

oai_token-act-pair · gpt-3.5-turbo

references to non-white individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fallacy

-0.88

 downfall

-0.87

 mock

-0.82

 dilemma

-0.81

 ridicule

-0.81

 folly

-0.81

 undo

-0.80

 disguise

-0.80

 dossier

-0.78

 caveat

-0.77

POSITIVE LOGITS

citizens

1.55

white

1.45

members

1.38

resident

1.38

humans

1.36

Americans

1.35

wh

1.35

immigrant

1.33

married

1.31

profits

1.31

Activations Density 0.067%

phrases containing the prefix "non-" followed by a hyphen and a word

references to non-white individuals or groups

No Comments

No Known Activations