INDEX

Explanations

phrases that begin with "What's" or similar constructions

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "what."

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

 horizont

-0.78

 seiz

-0.70

zn

-0.66

Buyable

-0.63

 indoor

-0.62

Tid

-0.62

 Pact

-0.61

 Tome

-0.60

ortium

-0.60

 Shap

-0.59

POSITIVE LOGITS

¬

0.95

¡

0.90

ı

0.90

Â¢

0.86

º

0.84

Ķ

0.84

į

0.83

else

0.82

Ĳ

0.82

ª

0.79

Activations Density 0.093%

phrases that begin with "What's" or similar constructions

repeated instances of the word "what."

No Comments

No Known Activations