INDEX

Explanations

words related to a specific place or person

oai_token-act-pair · gpt-3.5-turbo

proper nouns referring to people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

gal

-0.68

 caution

-0.66

 Juno

-0.65

ibaba

-0.57

sow

-0.56

peg

-0.55

 scrap

-0.55

 reel

-0.54

Â¯

-0.54

 impulse

-0.53

POSITIVE LOGITS

ulhu

1.19

pillar

1.03

berus

1.00

ortium

0.92

emporary

0.86

etary

0.85

igham

0.85

aminer

0.79

estial

0.78

cled

0.78

Activations Density 0.093%

words related to a specific place or person

proper nouns referring to people and places

No Comments

No Known Activations