INDEX

Explanations

references to political regimes

oai_token-act-pair · gpt-3.5-turbo

mentions of governmental authority or control, particularly referring to regimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Lent

-0.88

sight

-0.78

lder

-0.75

Universal

-0.73

furt

-0.73

ritch

-0.72

 Spiel

-0.72

 Loch

-0.70

Redd

-0.69

eting

-0.68

POSITIVE LOGITS

 regimes

0.99

 regime

0.98

 overthrow

0.85

 dictatorship

0.83

 dictators

0.80

 overth

0.80

archs

0.79

 dictator

0.79

 milit

0.78

 imposed

0.76

Activations Density 0.026%

references to political regimes

mentions of governmental authority or control, particularly referring to regimes

No Comments

No Known Activations