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

affer

-0.73

antry

-0.69

orce

-0.69

wear

-0.69

ury

-0.67

achy

-0.66

speed

-0.66

ous

-0.65

poral

-0.64

thouse

-0.63

POSITIVE LOGITS

RAW

0.72

 Remastered

0.66

clus

0.64

 advoc

0.63

 Templ

0.62

Pv

0.62

 parting

0.62

ECD

0.61

 Mines

0.61

 defic

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.