INDEX

Explanations

No Explanations Found

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

 contrace

-0.92

 elig

-0.86

aeda

-0.79

idia

-0.73

acebook

-0.73

reditary

-0.70

interstitial

-0.70

ibaba

-0.70

Interstitial

-0.69

zbollah

-0.69

POSITIVE LOGITS

ridge

0.69

velop

0.68

ifier

0.66

Sys

0.65

serv

0.64

 Merry

0.64

Launch

0.63

SpaceEngineers

0.62

rather

0.62

Det

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.