INDEX

Explanations

numeric values, decimals or percentages

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation or formatting changes in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hene

-0.85

ividual

-0.85

 mosqu

-0.80

utsche

-0.74

 communication

-0.70

earchers

-0.69

 pinpoint

-0.68

 withdrawing

-0.66

sterdam

-0.66

 econom

-0.65

POSITIVE LOGITS

Appearances

1.59

Contents

1.58

Trivia

1.57

Characters

1.50

Gallery

1.37

pmwiki

1.36

Episode

1.31

Gameplay

1.17

Spoiler

1.13

Season

1.13

Activations Density 0.297%

numeric values, decimals or percentages

instances of punctuation or formatting changes in the text

No Comments

No Known Activations