INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

words related to locations, institutions, and significant dates or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 corrid

-0.62

ÃįÃį

-0.59

ãĥ¡

-0.55

Lear

-0.54

omorph

-0.53

awa

-0.53

pload

-0.53

 predec

-0.52

ãģĤ

-0.52

 Pengu

-0.52

POSITIVE LOGITS

 Copyright

0.72

 Belfast

0.69

 ensured

0.66

↵

0.66

 =================================

0.63

↵Âł

0.63

 Â©

0.62

 greets

0.61

utterstock

0.60

↵↵

0.60

Activations Density 0.754%

locations or places

words related to locations, institutions, and significant dates or events

No Comments

No Known Activations