INDEX

Explanations

phrases related to various social movements

oai_token-act-pair · gpt-3.5-turbo

references to social or political movements

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

oba

-0.68

 juicy

-0.68

ilk

-0.63

é¾įå

-0.63

acho

-0.62

CRIP

-0.62

clusions

-0.61

 Appears

-0.61

 chunks

-0.61

ãĥ¤

-0.60

POSITIVE LOGITS

 movement

1.17

 movements

0.99

naire

0.95

 Movement

0.94

ĸļ

0.92

naires

0.84

ivism

0.79

 agitation

0.77

move

0.74

 activists

0.73

Activations Density 0.019%

phrases related to various social movements

references to social or political movements

No Comments

No Known Activations