INDEX

Explanations

phrases related to opinions and actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 corrid

-0.56

 pend

-0.52

 referen

-0.51

 Rober

-0.51

ueless

-0.50

 millenn

-0.50

ificant

-0.49

Higher

-0.49

 conclud

-0.49

Compar

-0.48

POSITIVE LOGITS

Ĥİ

0.58

SourceFile

0.57

bra

0.56

 Uncharted

0.52

isons

0.51

TOR

0.51

tesy

0.51

rawdownloadcloneembedreportprint

0.50

Vert

0.50

hirt

0.49

Activations Density 1.215%

phrases related to opinions and actions

phrases indicating uncertainty or speculation

No Comments

No Known Activations