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

Exp

-0.73

 Universal

-0.67

Yor

-0.66

Ur

-0.65

 Trop

-0.65

 Commons

-0.63

polit

-0.63

 Democr

-0.61

RP

-0.61

 Geographic

-0.60

POSITIVE LOGITS

PsyNetMessage

0.83

avement

0.76

AAAA

0.76

EY

0.71

 counselling

0.70

etting

0.70

anon

0.70

arnaev

0.69

atonin

0.69

aking

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.