INDEX

Explanations

live-action related terms

oai_token-act-pair · gpt-3.5-turbo

references to live-action content

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

Īè

-0.73

selage

-0.71

>>\

-0.69

Ĥİ

-0.68

²¾

-0.66

 junction

-0.64

maj

-0.64

 aster

-0.64

perty

-0.63

 Huss

-0.63

POSITIVE LOGITS

Journal

0.81

atten

0.79

motion

0.73

DonaldTrump

0.72

 breathed

0.71

amed

0.70

Tweet

0.70

ouver

0.69

Interstitial

0.69

stream

0.68

Activations Density 0.078%

live-action related terms

references to live-action content

No Comments

No Known Activations