INDEX

Explanations

terms related to voting

oai_token-act-pair · gpt-3.5-turbo

references to voting and electoral processes

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

Not in Any Lists

No Comments

Negative Logits

peria

-0.85

ologically

-0.81

Else

-0.80

 tremend

-0.76

Mount

-0.73

obar

-0.72

cms

-0.72

ĸļ

-0.72

olog

-0.71

ENSE

-0.71

POSITIVE LOGITS

 voting

1.03

 machines

0.90

 booths

0.84

 ballots

0.84

 irregularities

0.83

 votes

0.81

 turnout

0.77

 vote

0.76

eering

0.75

oting

0.75

Activations Density 0.014%

terms related to voting

references to voting and electoral processes

No Comments

No Known Activations