INDEX

Explanations

objects and actions related to smoking and weapons

oai_token-act-pair · gpt-3.5-turbo

references to tobacco products 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 partName

-0.78

yss

-0.74

tics

-0.74

Ü

-0.73

 Livingston

-0.71

tical

-0.69

 MacDonald

-0.67

 Holt

-0.65

erenn

-0.65

å§«

-0.65

POSITIVE LOGITS

 cigars

1.05

 cigar

1.01

illo

0.97

arette

0.94

 wrapper

0.92

inals

0.79

Wra

0.79

ensis

0.79

 humid

0.78

pipe

0.77

Activations Density 0.012%

objects and actions related to smoking and weapons

references to tobacco products and related imagery

No Comments

No Known Activations