INDEX

Explanations

phrases related to voting and political decisions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "voted."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ebin

-0.78

clair

-0.76

illin

-0.75

ptoms

-0.75

fal

-0.72

DragonMagazine

-0.70

qv

-0.70

uras

-0.70

vern

-0.69

ology

-0.68

POSITIVE LOGITS

 unanimously

0.93

room

0.75

 overwhelmingly

0.75

ndum

0.74

YES

0.73

 Leave

0.73

 differently

0.72

 against

0.72

 blindly

0.69

 Audit

0.69

Activations Density 0.027%

phrases related to voting and political decisions

instances of the word "voted."

No Comments

No Known Activations