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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

metics

-0.86

ged

-0.81

sey

-0.71

Rew

-0.66

gew

-0.66

lem

-0.64

etry

-0.64

pir

-0.63

bys

-0.62

ienne

-0.61

POSITIVE LOGITS

icter

0.83

URI

0.80

0.77

 convol

0.71

 skelet

0.70

 Pavel

0.69

éĹĺ

0.67

psi

0.66

METHOD

0.65

Inv

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.