INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Kush

-0.72

bern

-0.67

ovych

-0.67

cham

-0.66

 Haku

-0.65

XP

-0.65

ournals

-0.65

Ken

-0.62

Hak

-0.62

 Chatt

-0.62

POSITIVE LOGITS

 rehe

0.80

lob

0.73

annon

0.72

ocious

0.71

 rehearsal

0.69

ROR

0.68

 staging

0.67

 rehears

0.67

communications

0.64

cffffcc

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.