INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bda

-0.88

inav

-0.84

tsy

-0.79

edia

-0.76

arent

-0.75

acca

-0.74

axies

-0.71

 includ

-0.67

 Skydragon

-0.66

editor

-0.65

POSITIVE LOGITS

 Wilkinson

0.72

 Thib

0.67

 Garr

0.66

Raf

0.64

staff

0.64

jay

0.63

nt

0.61

 Noon

0.59

Var

0.59

Kra

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.