INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

phabet

-0.95

thouse

-0.84

earchers

-0.76

anchester

-0.71

ylum

-0.70

rompt

-0.68

inguished

-0.68

apy

-0.65

angered

-0.65

monds

-0.65

POSITIVE LOGITS

 Solitaire

0.85

å£«

0.67

enegger

0.67

fighters

0.64

fighter

0.64

schild

0.60

ãģĤ

0.60

gins

0.60

 kidnapped

0.59

 Jericho

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.