INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ilk

-0.68

opal

-0.67

undo

-0.66

 bloodstream

-0.66

fitting

-0.64

 hemisphere

-0.63

plement

-0.62

ctica

-0.62

izoph

-0.61

igmat

-0.60

POSITIVE LOGITS

illard

1.29

rand

0.78

ville

0.75

 Dunn

0.73

stall

0.73

 Lowe

0.71

yard

0.71

erness

0.70

ieri

0.69

stown

0.68

Activations Density 0.008%

names of individuals

proper nouns, specifically names of individuals and entities

No Comments

No Known Activations