INDEX

Explanations

mentions of the concept of "autonomy."

oai_token-act-pair · gpt-3.5-turbo

concepts related to autonomy and self-governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Ing

-0.76

ibur

-0.75

Ö¼

-0.74

×Ķ

-0.74

×Ĳ

-0.72

Ger

-0.72

×Ļ×

-0.72

si

-0.71

ttp

-0.71

Comments

-0.68

POSITIVE LOGITS

 autonomy

1.03

onomy

0.91

ignty

0.91

onomous

0.83

 challeng

0.82

 municip

0.81

essor

0.80

ensical

0.79

 embodied

0.78

 territ

0.77

Activations Density 0.005%

mentions of the concept of "autonomy."

concepts related to autonomy and self-governance

No Comments

No Known Activations