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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aspers

-0.86

ĸļ

-0.76

acca

-0.74

 opio

-0.72

ovember

-0.69

Pas

-0.69

edIn

-0.69

ococ

-0.69

omed

-0.68

 Lump

-0.68

POSITIVE LOGITS

 revolving

0.68

plane

0.67

ship

0.67

footed

0.66

 Conan

0.66

rower

0.63

cake

0.62

rocket

0.62

 Shake

0.61

 Samurai

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.