INDEX

Explanations

names of individuals, particularly those involved in studies, businesses, or politics

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people, companies, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Sabha

-0.64

UGE

-0.62

uminati

-0.61

berra

-0.61

sembly

-0.60

ascade

-0.58

interstitial

-0.57

ibli

-0.57

acas

-0.56

uffed

-0.56

POSITIVE LOGITS

 recommends

0.93

 proposes

0.89

 emphasizes

0.82

 advises

0.77

 reminds

0.77

 suggests

0.77

 argues

0.76

 demonstrates

0.76

 encourages

0.76

 cites

0.72

Activations Density 0.707%

names of individuals, particularly those involved in studies, businesses, or politics

proper nouns, specifically names of people, companies, and organizations

No Comments

No Known Activations