INDEX

Explanations

terms related to censorship

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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

MER

-0.68

 Finn

-0.64

WORK

-0.63

Dew

-0.63

NO

-0.63

 Baker

-0.62

 Davidson

-0.62

 Eston

-0.61

 Kush

-0.61

odka

-0.60

POSITIVE LOGITS

orious

1.25

zers

1.04

oring

0.98

zer

0.96

orship

0.95

ors

0.90

asing

0.89

uses

0.89

 cens

0.84

ussen

0.84

Activations Density 0.042%

terms related to censorship

terms related to censorship and its implications

No Comments

No Known Activations