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

sonian

-0.82

å§«

-0.78

ãĥ¯ãĥ³

-0.73

IAS

-0.72

Fan

-0.72

ĳå£«

-0.72

Reply

-0.69

Roll

-0.68

Preview

-0.67

Reviewer

-0.67

POSITIVE LOGITS

 governance

0.70

arios

0.68

 nomination

0.66

 candidacy

0.65

iquette

0.65

 affili

0.65

 handshake

0.63

acea

0.63

 affiliation

0.63

 Warriors

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.