INDEX

Explanations

the word "scratch" and related terms

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "scratching" or starting from scratch

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

agonist

-0.78

CVE

-0.73

rid

-0.67

agements

-0.65

ihar

-0.64

uned

-0.63

quickShipAvailable

-0.62

AAF

-0.62

anchester

-0.62

acl

-0.61

POSITIVE LOGITS

 scratched

0.88

manship

0.87

 scratch

0.86

bones

0.86

pad

0.80

 slate

0.79

 itch

0.75

eting

0.74

ETS

0.72

bone

0.72

Activations Density 0.042%

the word "scratch" and related terms

phrases related to the concept of "scratching" or starting from scratch

No Comments

No Known Activations