INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 ..."

-0.61

 variance

-0.59

taboola

-0.52

Big

-0.49

Sorry

-0.49

 convol

-0.48

ãĥ©ãĥ³

-0.48

 attachments

-0.48

 marijuana

-0.47

 SPORTS

-0.47

POSITIVE LOGITS

ragon

0.73

oglu

0.69

unia

0.66

hyde

0.64

imore

0.64

Ã«

0.62

ghan

0.61

ossier

0.61

agate

0.60

illus

0.60

Activations Density 0.599%

proper nouns related to individuals

proper nouns and names

No Comments

No Known Activations