INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

CTV

-0.75

 predominantly

-0.66

league

-0.66

âĵĺ

-0.64

 Bapt

-0.63

 predomin

-0.61

 Academy

-0.61

aer

-0.61

 Alexand

-0.61

 League

-0.60

POSITIVE LOGITS

onym

0.73

pic

0.72

 sidel

0.66

onyms

0.66

 spinach

0.64

offs

0.63

anus

0.62

arin

0.62

 Saud

0.62

illance

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.