INDEX

Explanations

terms related to censorship and blocking

oai_token-act-pair · gpt-3.5-turbo

terms related to censorship and its implications

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

ilater

-0.76

itness

-0.74

verty

-0.73

ndra

-0.73

amac

-0.72

docker

-0.71

swick

-0.70

ptoms

-0.67

ancial

-0.67

ammad

-0.66

POSITIVE LOGITS

 cens

0.91

 censorship

0.85

 censor

0.77

 censored

0.76

zers

0.74

jing

0.72

orious

0.69

 levied

0.68

monkey

0.64

cens

0.64

Activations Density 0.036%

terms related to censorship and blocking

terms related to censorship and its implications

No Comments

No Known Activations