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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ividual

-0.91

igers

-0.84

aban

-0.81

etimes

-0.80

 Rouge

-0.78

gin

-0.74

zeb

-0.74

ucle

-0.72

abre

-0.72

gem

-0.71

POSITIVE LOGITS

EngineDebug

0.79

ç«

0.69

 Psal

0.65

Aust

0.64

 symbolism

0.64

 Kuala

0.64

åī

0.63

 teachings

0.61

Lens

0.61

 prescriptions

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.