INDEX

Explanations

mentions of land measurements

oai_token-act-pair · gpt-3.5-turbo

references to land area measurements

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

 cumbers

-0.67

 initiation

-0.66

 wearer

-0.65

 compulsion

-0.65

Doctors

-0.62

 surgical

-0.59

 glove

-0.59

anwhile

-0.59

 Crim

-0.59

POS

-0.58

POSITIVE LOGITS

 acres

1.41

 acre

1.18

 hectares

1.16

acre

1.01

renheit

0.90

 farmland

0.88

terness

0.87

flower

0.83

 ranch

0.82

grain

0.79

Activations Density 0.007%

mentions of land measurements

references to land area measurements

No Comments

No Known Activations