INDEX

Explanations

references to anonymity or people/activities hiding their identity

oai_token-act-pair · gpt-3.5-turbo

references to anonymity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

union

-0.86

rehens

-0.83

neys

-0.79

hews

-0.78

NEY

-0.76

emark

-0.73

ynski

-0.73

enburg

-0.73

bourg

-0.72

Ħ¢

-0.71

POSITIVE LOGITS

 informant

0.94

onym

0.94

 anonymous

0.85

 anonym

0.82

 anonymity

0.80

 anonymously

0.77

tip

0.77

 informants

0.76

 sourcing

0.75

onymous

0.73

Activations Density 0.050%

references to anonymity or people/activities hiding their identity

references to anonymity

No Comments

No Known Activations