INDEX

Explanations

mentions of voting or votes

oai_token-act-pair · gpt-3.5-turbo

references to voting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 unden

-0.94

 Palestin

-0.87

 millenn

-0.85

ccording

-0.80

inav

-0.80

 tremend

-0.80

£ı

-0.80

etheless

-0.76

ãĤ¨ãĥ«

-0.74

 colon

-0.70

POSITIVE LOGITS

 vote

1.31

vote

1.27

 votes

1.26

 Vote

1.22

 Votes

0.98

votes

0.97

 voting

0.96

Vote

0.92

board

0.91

 ballots

0.90

Activations Density 0.024%

mentions of voting or votes

references to voting

No Comments

No Known Activations