INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns or names

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

 coerc

-0.63

assetsadobe

-0.61

 monop

-0.60

rud

-0.59

 airst

-0.57

rontal

-0.57

atre

-0.56

 mathemat

-0.56

 psychiat

-0.56

-0.53

POSITIVE LOGITS

Äĵ

0.67

igo

0.65

Åį

0.62

 Prescott

0.59

Å«

0.57

Ä«

0.55

hill

0.54

 Compton

0.53

idine

0.53

Hon

0.53

Activations Density 0.721%

proper nouns

specific proper nouns or names

No Comments

No Known Activations