INDEX

Explanations

references to articles from an archive

oai_token-act-pair · gpt-3.5-turbo

references to archived articles and their metadata

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

 alike

-0.68

 sequ

-0.58

CHO

-0.58

 lect

-0.57

naire

-0.55

 cake

-0.55

 Faust

-0.54

Gou

-0.53

 testifying

-0.53

 draw

-0.53

POSITIVE LOGITS

xp

0.72

edition

0.66

interstitial

0.66

Reader

0.65

imilation

0.64

cair

0.62

 editions

0.60

ãĥ¼ãĤ¯

0.60

igion

0.60

 Duration

0.58

Activations Density 0.127%

references to articles from an archive

references to archived articles and their metadata

No Comments

No Known Activations