INDEX

Explanations

politically-related names and terms

oai_token-act-pair · gpt-3.5-turbo

mentions of political figures and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Niet

-0.65

anwhile

-0.58

 Hiroshima

-0.58

mble

-0.54

FUL

-0.52

semble

-0.49

eatures

-0.48

Wem

-0.48

tml

-0.47

oenix

-0.46

POSITIVE LOGITS

's

0.76

Care

0.63

care

0.62

Semitism

0.61

ÃŃs

0.61

omics

0.55

 meddling

0.54

Â´

0.53

 anymore

0.52

ani

0.50

Activations Density 0.499%

politically-related names and terms

mentions of political figures and related contexts

No Comments

No Known Activations