INDEX

Explanations

mentions of extensions or additions

oai_token-act-pair · gpt-3.5-turbo

references to "extension" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

icial

-0.84

 VIDEOS

-0.76

zo

-0.73

vo

-0.73

 Conduct

-0.71

ivan

-0.71

zzi

-0.71

afa

-0.70

ards

-0.70

Edited

-0.70

POSITIVE LOGITS

 extension

1.40

 extensions

1.26

 ende

1.13

 applic

0.97

 therap

0.97

 confir

0.95

 exerc

0.94

 streng

0.92

 adolesc

0.88

 arrang

0.85

Activations Density 0.013%

mentions of extensions or additions

references to "extension" in various contexts

No Comments

No Known Activations