INDEX

Explanations

numbers related to percentages or quantities

oai_token-act-pair · gpt-3.5-turbo

expressions indicating exclusivity or limitation

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

insula

-0.73

 charism

-0.73

 largeDownload

-0.71

finder

-0.65

align

-0.64

 PLUS

-0.58

 shenan

-0.58

 Niet

-0.56

multipl

-0.56

ahime

-0.55

POSITIVE LOGITS

 marginally

0.98

ices

0.81

ICES

0.78

 scratches

0.76

ifiable

0.72

othing

0.72

Ń·

0.71

 minor

0.71

 limited

0.71

oor

0.70

Activations Density 0.050%

numbers related to percentages or quantities

expressions indicating exclusivity or limitation

No Comments

No Known Activations