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

 glim

-0.81

adows

-0.76

umbn

-0.72

inately

-0.65

assic

-0.65

esides

-0.65

 distingu

-0.64

owship

-0.63

 predators

-0.62

 intrig

-0.62

POSITIVE LOGITS

Mo

0.75

 Jian

0.74

erman

0.68

 Worth

0.67

 Conn

0.66

 Resolution

0.65

PF

0.64

Rus

0.64

 Consent

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.