INDEX

Explanations

terms related to different types of interactions, such as "interfering," "interdependence," "interactions," and "intercollegiate."

oai_token-act-pair · gpt-3.5-turbo

words and terms related to various types of interdependencies and relationships

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

 Cinderella

-0.59

Cly

-0.56

 worms

-0.56

 apples

-0.55

 Doctrine

-0.55

Imm

-0.55

 TAMADRA

-0.55

 Feast

-0.54

keyes

-0.53

 Valkyrie

-0.53

POSITIVE LOGITS

poral

0.96

allic

0.95

xual

0.92

etary

0.92

cheon

0.84

incial

0.83

ateral

0.80

utory

0.79

artment

0.79

cular

0.78

Activations Density 0.081%

terms related to different types of interactions, such as "interfering," "interdependence," "interactions," and "intercollegiate."

words and terms related to various types of interdependencies and relationships

No Comments

No Known Activations