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

cross

-0.74

ds

-0.71

vine

-0.67

 dstg

-0.66

 grate

-0.65

cas

-0.65

---------

-0.65

*/

-0.64

SourceFile

-0.63

 PLEASE

-0.63

POSITIVE LOGITS

clusions

0.96

 relation

0.95

 conjunction

0.91

 regards

0.88

ordinate

0.84

 accordance

0.83

offensive

0.83

clus

0.81

effic

0.81

 vain

0.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.