INDEX

Explanations

names of people and organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

 repressive

-0.62

 Cinderella

-0.60

 prostitutes

-0.59

 Presidents

-0.59

tumblr

-0.59

 accommod

-0.58

 manipulating

-0.57

 progresses

-0.57

 definite

-0.57

 affects

-0.57

POSITIVE LOGITS

(@

1.00

Jr

0.86

elli

0.85

QC

0.83

enstein

0.82

meyer

0.82

inger

0.82

zinski

0.82

baum

0.81

croft

0.81

Activations Density 0.205%

names of people and organizations

proper nouns, particularly names of individuals

No Comments

No Known Activations