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

 Remastered

-0.69

ffen

-0.66

 Mahjong

-0.65

naires

-0.64

illance

-0.63

naire

-0.62

rix

-0.62

antle

-0.62

RAG

-0.61

aum

-0.60

POSITIVE LOGITS

 CLASS

0.71

Cav

0.63

èĢħ

0.62

Ã£

0.60

 ---------

0.58

======

0.57

 resemblance

0.57

 resemb

0.57

 alas

0.57

Appearance

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.