INDEX

Explanations

words related to place names

oai_token-act-pair · gpt-3.5-turbo

the letter 'w' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uate

-0.77

 distingu

-0.66

 paraly

-0.65

 conscientious

-0.65

âĸ¬

-0.63

âĸ¬âĸ¬

-0.61

 culp

-0.61

 scapego

-0.61

 fixing

-0.60

 correlation

-0.60

POSITIVE LOGITS

elcome

1.40

itness

1.39

atts

1.23

isdom

1.22

izard

1.18

ashington

1.17

atcher

1.15

arranted

1.13

ield

1.10

rought

1.09

Activations Density 0.045%

words related to place names

the letter 'w' in various contexts

No Comments

No Known Activations