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

iann

-0.80

alian

-0.70

utsch

-0.70

ammy

-0.69

ivari

-0.68

VIDIA

-0.68

fman

-0.66

agnetic

-0.66

 consecut

-0.65

ount

-0.65

POSITIVE LOGITS

 Taken

0.81

CoC

0.72

 Such

0.71

 Cannot

0.70

 Acad

0.69

 Called

0.69

 Aires

0.68

 Therefore

0.67

 Cooking

0.67

 Saving

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.