INDEX

Explanations

phrases indicating explanation or clarification

oai_token-act-pair · gpt-3.5-turbo

empty text or separators indicating no 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ©

-0.64

ãĥ¯ãĥ³

-0.61

ãĤ´ãĥ³

-0.59

venth

-0.58

ãĥ³ãĤ¸

-0.56

æĿ

-0.54

rounded

-0.54

Â¢

-0.54

ayed

-0.54

obbies

-0.54

POSITIVE LOGITS

 Allaah

0.71

 Canaver

0.70

 Xiaomi

0.66

 Chomsky

0.65

 graphene

0.64

 astronomers

0.64

 SpaceX

0.63

 ISPs

0.62

 Melania

0.61

 there

0.61

Activations Density 0.633%

phrases indicating explanation or clarification

empty text or separators indicating no content

No Comments

No Known Activations