INDEX

Explanations

references to retrofitting or modifications made to improve or update something

oai_token-act-pair · gpt-3.5-turbo

references to retro themes or styles

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

avanaugh

-0.75

gow

-0.73

illary

-0.71

FUL

-0.68

MSN

-0.66

 Marketable

-0.66

 Parenthood

-0.64

RAW

-0.62

UGE

-0.62

gans

-0.62

POSITIVE LOGITS

actively

1.42

active

1.27

spective

1.14

fitted

1.07

gradation

1.01

fit

1.01

grade

0.98

 retro

0.97

fits

0.95

spection

0.94

Activations Density 0.018%

references to retrofitting or modifications made to improve or update something

references to retro themes or styles

No Comments

No Known Activations