INDEX

Explanations

mentions of voters in political contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of voters and voting behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uner

-0.63

claimer

-0.61

rend

-0.61

esc

-0.61

rack

-0.60

 Shack

-0.60

imen

-0.60

cub

-0.60

 Mehran

-0.59

TAG

-0.59

POSITIVE LOGITS

 voters

3.65

 Voters

2.98

 voter

2.21

 electors

2.10

 ballots

2.06

 electorate

2.00

oters

1.97

 votes

1.96

 Voter

1.79

 voting

1.75

Activations Density 0.013%

mentions of voters in political contexts

mentions of voters and voting behavior

No Comments

No Known Activations