INDEX

Explanations

words or phrases indicating a direct or indirect connection between two entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating associations or links between various concepts

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

DragonMagazine

-0.87

matched

-0.87

Reviewed

-0.81

-|

-0.80

hari

-0.76

olit

-0.72

icer

-0.70

anooga

-0.69

iken

-0.69

ies

-0.68

POSITIVE LOGITS

 criminality

0.88

 terrorism

0.84

 assass

0.79

 unlocking

0.77

 witchcraft

0.76

 increased

0.75

 longevity

0.74

 crime

0.73

 excellence

0.73

 theft

0.73

Activations Density 0.164%

words or phrases indicating a direct or indirect connection between two entities

phrases indicating associations or links between various concepts

No Comments

No Known Activations