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

AVG

-0.71

UGE

-0.70

¼

-0.69

avorite

-0.69

keyes

-0.65

ils

-0.63

ĸļ

-0.63

sylv

-0.62

 neurot

-0.62

pps

-0.61

POSITIVE LOGITS

amber

0.71

abases

0.70

blogs

0.69

 Puzzles

0.64

founded

0.63

ambers

0.61

 Zion

0.61

 Centauri

0.61

stairs

0.61

endez

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.