INDEX

Explanations

references to the word "Wool"

oai_token-act-pair · gpt-3.5-turbo

references to wool

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

 Aval

-0.70

 Explain

-0.69

 Hiroshima

-0.68

 citation

-0.67

Oro

-0.65

CENT

-0.65

 Cuomo

-0.63

INF

-0.63

 Referred

-0.62

 Activate

-0.62

POSITIVE LOGITS

wich

1.16

sey

1.08

worth

1.07

wyn

1.03

awei

1.02

nesday

0.97

enn

0.96

worms

0.96

igan

0.95

isine

0.94

Activations Density 0.004%

references to the word "Wool"

references to wool

No Comments

No Known Activations