INDEX

Explanations

locations or directions within a document

oai_token-act-pair · gpt-3.5-turbo

phrases indicating relational or contextual connections

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

 NAME

-0.55

Name

-0.54

 Medals

-0.54

 Numbers

-0.52

 Tradable

-0.52

 Males

-0.52

 numbering

-0.52

ewitness

-0.52

 Families

-0.52

 individuals

-0.51

POSITIVE LOGITS

EStream

0.66

é¾įåĸļå£«

0.58

FontSize

0.57

itto

0.56

×¨

0.54

hetti

0.53

arde

0.51

lio

0.51

against

0.50

owitz

0.49

Activations Density 0.901%

locations or directions within a document

phrases indicating relational or contextual connections

No Comments

No Known Activations