INDEX

Explanations

references to the word "Wool"

oai_token-act-pair · gpt-3.5-turbo

references to wool and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 citation

-0.74

 Aval

-0.68

 Explain

-0.67

 Referred

-0.65

 Hiroshima

-0.65

avez

-0.65

 ADHD

-0.64

INF

-0.63

 exception

-0.62

DUI

-0.62

POSITIVE LOGITS

awei

1.18

wich

1.11

worth

1.05

 Wool

1.04

sey

1.03

nesday

1.01

worms

0.99

wyn

0.96

enn

0.93

heed

0.92

Activations Density 0.004%

references to the word "Wool"

references to wool and related terms

No Comments

No Known Activations