INDEX

Explanations

proper nouns related to people, locations, and organizations

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of specific individuals and their roles or attributes within a context

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

 Siber

-0.82

 Kirby

-0.78

 Haram

-0.72

 Atkinson

-0.71

KC

-0.69

 Tinker

-0.69

 Misty

-0.69

 Chiefs

-0.68

 SERVICE

-0.67

Nid

-0.66

POSITIVE LOGITS

geist

1.03

uchin

1.02

nuts

0.96

ollower

0.92

igans

0.89

iae

0.88

arist

0.84

olin

0.84

iano

0.83

auer

0.81

Activations Density 0.018%

proper nouns related to people, locations, and organizations

repeated mentions of specific individuals and their roles or attributes within a context

No Comments

No Known Activations