INDEX

Explanations

mentions of editors-in-chief or other leadership positions in news organizations

oai_token-act-pair · gpt-3.5-turbo

references to editorial positions and roles in media organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Dickinson

-0.87

 Bullets

-0.77

 plaus

-0.74

 Burr

-0.66

 hitch

-0.65

ulhu

-0.64

 bleach

-0.63

 Helic

-0.63

 Dunk

-0.63

 Meadows

-0.62

POSITIVE LOGITS

turned

1.23

friendly

1.08

elect

1.07

cum

1.03

design

1.00

director

0.98

training

0.97

general

0.97

inspired

0.97

controlled

0.96

Activations Density 0.094%

mentions of editors-in-chief or other leadership positions in news organizations

references to editorial positions and roles in media organizations

No Comments

No Known Activations