INDEX

Explanations

specific proper nouns

oai_token-act-pair · gpt-3.5-turbo

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

 gestation

-0.67

pse

-0.66

 flares

-0.63

 levers

-0.63

generated

-0.63

 Proposition

-0.61

Osw

-0.60

 STATE

-0.60

Reviewer

-0.60

 Reich

-0.59

POSITIVE LOGITS

irs

0.86

auld

0.84

ilver

0.81

ault

0.79

iro

0.78

aud

0.78

iba

0.78

yrs

0.76

oise

0.75

uple

0.75

Activations Density 0.211%

specific proper nouns

No Comments

No Known Activations