INDEX

Explanations

references to behavior or actions related to conducting oneself in a specific manner

oai_token-act-pair · gpt-3.5-turbo

instances of the word "conduct" and its variations, typically in contexts related to behavior or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

cube

-0.66

Kids

-0.64

istan

-0.64

corn

-0.64

 Nightmares

-0.63

LOAD

-0.60

NCT

-0.60

username

-0.60

iewicz

-0.59

arger

-0.59

POSITIVE LOGITS

ivity

1.18

ors

1.17

uations

1.01

ivities

0.94

ional

0.94

ively

0.89

onduct

0.87

ives

0.85

atted

0.85

ive

0.82

Activations Density 0.060%

references to behavior or actions related to conducting oneself in a specific manner

instances of the word "conduct" and its variations, typically in contexts related to behavior or actions

No Comments

No Known Activations