INDEX

Explanations

terms related to politics and elections

oai_token-act-pair · gpt-3.5-turbo

references to electoral and governmental structures

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iasis

-0.72

paren

-0.68

occ

-0.66

ijk

-0.65

ofi

-0.65

Else

-0.64

apan

-0.63

itars

-0.63

grave

-0.62

oglu

-0.62

POSITIVE LOGITS

 electorate

1.16

eering

1.08

eers

0.94

rons

0.81

 constituency

0.79

 voters

0.75

 polling

0.73

 constituencies

0.73

 fray

0.72

 voting

0.72

Activations Density 0.009%

terms related to politics and elections

references to electoral and governmental structures

No Known Activations