INDEX

Explanations

keywords related to coffins

oai_token-act-pair · gpt-3.5-turbo

references to coffins and related imagery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Express

-0.78

ãĥ£

-0.76

onomy

-0.76

 Trib

-0.74

 Berman

-0.74

SN

-0.74

ãĥ³ãĤ¸

-0.73

TAG

-0.73

Ô

-0.72

Madison

-0.71

POSITIVE LOGITS

 coffin

1.43

 coff

0.97

milo

0.95

 curtains

0.86

raints

0.81

rontal

0.81

lid

0.80

inery

0.79

hemy

0.78

 Coffin

0.78

Activations Density 0.014%

keywords related to coffins

references to coffins and related imagery

No Comments

No Known Activations