INDEX

Explanations

proper nouns related to the name "Lew" or "Lewinsky."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lew."

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

ACTED

-0.90

CHR

-0.74

 à¨

-0.73

expr

-0.72

OPLE

-0.69

ãĥ¼ãĥĨ

-0.68

thood

-0.66

 bulls

-0.66

PDATE

-0.65

¥µ

-0.64

POSITIVE LOGITS

andowski

1.43

insky

1.08

enstein

0.94

ington

0.94

inski

0.92

lem

0.89

izard

0.84

Lew

0.83

ield

0.82

itsch

0.80

Activations Density 0.016%

proper nouns related to the name "Lew" or "Lewinsky."

mentions of the name "Lew."

No Comments

No Known Activations