INDEX

Explanations

mentions of specific names

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names

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

aman

-0.76

berman

-0.76

romy

-0.73

alus

-0.72

ron

-0.70

some

-0.69

avi

-0.68

live

-0.66

imum

-0.66

ophon

-0.65

POSITIVE LOGITS

 Scion

0.69

Tuc

0.68

 Inquisition

0.68

 hemisphere

0.65

orsche

0.65

pires

0.64

uries

0.63

Duc

0.62

 bleeding

0.62

 Kits

0.62

Activations Density 0.000%

mentions of specific names

proper nouns and names

No Comments

No Known Activations