INDEX

Explanations

mentions and descriptions of specific events, people, or places

oai_token-act-pair · gpt-3.5-turbo

references to key figures or events in political and social contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Starcraft

-0.58

 cosmos

-0.58

âĻ¥

-0.52

ze

-0.52

Transform

-0.52

 imaginary

-0.52

 melanch

-0.51

laughs

-0.51

 Clockwork

-0.51

!).

-0.51

POSITIVE LOGITS

 briefed

0.72

enegger

0.69

nesty

0.65

 spokeswoman

0.65

arnaev

0.64

 blamed

0.64

 bolstered

0.63

 alarmed

0.63

 halted

0.62

 spokesman

0.62

Activations Density 4.212%

mentions and descriptions of specific events, people, or places

references to key figures or events in political and social contexts

No Comments

No Known Activations