INDEX

Explanations

the word "California"

oai_token-act-pair · gpt-3.5-turbo

mentions of California

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

htar

-0.95

chel

-0.79

Ott

-0.75

alsh

-0.74

sworth

-0.72

isen

-0.68

Ò

-0.66

hern

-0.65

 Belarus

-0.65

lift

-0.65

POSITIVE LOGITS

 Edison

0.98

 Calif

0.88

Oro

0.88

ornia

0.84

 Springs

0.83

 wildfires

0.82

 Penal

0.82

 Unified

0.82

 Superior

0.81

 Proposition

0.80

Activations Density 0.043%

the word "California"

mentions of California

No Comments

No Known Activations