INDEX

Explanations

PG-related terms or codes

oai_token-act-pair · gpt-3.5-turbo

references to a character or content related to PG-rated media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ufact

-0.82

cess

-0.74

alities

-0.72

puter

-0.71

hold

-0.70

ality

-0.69

pins

-0.68

fty

-0.67

combe

-0.66

andowski

-0.66

POSITIVE LOGITS

omez

1.27

allery

1.01

raphic

0.97

ORGE

0.96

roups

0.95

ENC

0.94

raph

0.93

ENE

0.92

HHHH

0.91

onz

0.88

Activations Density 0.073%

PG-related terms or codes

references to a character or content related to PG-rated media

No Comments

No Known Activations