INDEX

Explanations

phrases indicating an approximation or range

oai_token-act-pair · gpt-3.5-turbo

phrases that express uncertainty or variability in a statement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 corridors

-0.65

Cy

-0.61

 EDITION

-0.58

 Puzz

-0.58

 Vector

-0.56

bourg

-0.54

 juggling

-0.53

ynski

-0.52

 Mane

-0.52

AIR

-0.52

POSITIVE LOGITS

nery

1.12

leans

1.12

chard

1.11

lando

1.08

nam

0.97

acle

0.94

chid

0.94

gin

0.92

phan

0.91

acular

0.90

Activations Density 0.035%

phrases indicating an approximation or range

phrases that express uncertainty or variability in a statement

No Comments

No Known Activations