INDEX

Explanations

mentions of political officials, actions, and positions

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their roles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fibers

-0.71

itars

-0.70

ibaba

-0.70

 intersection

-0.65

MpServer

-0.65

 mats

-0.65

 extraction

-0.64

nings

-0.63

 conditioning

-0.63

nergy

-0.63

POSITIVE LOGITS

 appointed

0.95

 veto

0.95

 appoint

0.93

 assassinated

0.89

 appointing

0.87

 Office

0.84

 office

0.84

 presided

0.83

 resign

0.82

 nominated

0.79

Activations Density 0.576%

mentions of political officials, actions, and positions

references to political figures and their roles

No Comments

No Known Activations