INDEX

Explanations

references to political candidates

oai_token-act-pair · gpt-3.5-turbo

mentions of political candidates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

vironment

-0.86

ights

-0.79

olia

-0.75

wart

-0.74

tesy

-0.73

erie

-0.72

erial

-0.70

aline

-0.70

ŃĶ

-0.68

iencies

-0.67

POSITIVE LOGITS

 candidates

1.20

 candidate

1.19

idates

1.15

 Candidate

1.07

cand

0.93

 voters

0.87

 ballots

0.86

 nominee

0.85

Cand

0.83

 delegates

0.83

Activations Density 0.024%

references to political candidates

mentions of political candidates

No Comments

No Known Activations