INDEX

Explanations

references to media content or messaging

oai_token-act-pair · gpt-3.5-turbo

references to media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Salvador

-0.80

adian

-0.76

 damn

-0.75

 goddamn

-0.71

orney

-0.70

 polyg

-0.69

 pencil

-0.65

pired

-0.63

clus

-0.61

 Alfred

-0.61

POSITIVE LOGITS

Media

1.26

 playback

0.86

media

0.85

 VIDEOS

0.85

Wiki

0.82

Buzz

0.82

Sources

0.80

fax

0.79

 Reporter

0.77

eval

0.76

Activations Density 0.011%

references to media content or messaging

references to media content

No Comments

No Known Activations