INDEX

Explanations

words beginning with the letter "A" that may be part of a title or description

oai_token-act-pair · gpt-3.5-turbo

references to the article or report source

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Arcade

-0.73

angles

-0.72

Own

-0.69

arsity

-0.63

 Adin

-0.63

Contents

-0.62

Ó

-0.61

SIZE

-0.60

 amps

-0.60

Merit

-0.60

POSITIVE LOGITS

cknowled

1.30

 spokeswoman

1.20

 spokesman

1.15

 spokesperson

1.12

gency

0.99

usterity

0.96

ircraft

0.93

lyss

0.93

verages

0.92

 handful

0.91

Activations Density 0.154%

words beginning with the letter "A" that may be part of a title or description

references to the article or report source

No Comments

No Known Activations