INDEX

Explanations

references to specific organizations, websites, or individuals

oai_token-act-pair · gpt-3.5-turbo

references to political entities and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 uncont

-0.74

 semblance

-0.70

 vanished

-0.68

 throne

-0.68

 offence

-0.68

enegger

-0.66

 innocent

-0.66

 dormant

-0.65

 withdrawn

-0.64

*/(

-0.64

POSITIVE LOGITS

 Magazine

1.04

Week

0.95

Magazine

0.95

News

0.95

Wire

0.93

Blog

0.91

Street

0.91

Daily

0.87

Politics

0.87

Media

0.85

Activations Density 0.517%

references to specific organizations, websites, or individuals

references to political entities and media

No Comments

No Known Activations