INDEX

Explanations

names of specific individuals and entities

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vanished

-0.70

enegger

-0.69

 dormant

-0.66

*/(

-0.66

abiding

-0.66

 shove

-0.65

 vacated

-0.65

arnaev

-0.64

 uncont

-0.64

 oranges

-0.64

POSITIVE LOGITS

Week

0.95

News

0.91

Blog

0.86

NET

0.85

Daily

0.83

 Magazine

0.82

Politics

0.81

Econom

0.81

news

0.79

Media

0.78

Activations Density 0.397%

names of specific individuals and entities

references to specific organizations or entities

No Comments

No Known Activations