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

cius

-0.79

dyn

-0.70

fav

-0.70

terior

-0.68

Fav

-0.67

 artery

-0.65

 habitual

-0.65

 whence

-0.62

 overc

-0.61

 democratically

-0.61

POSITIVE LOGITS

anamo

0.77

pac

0.72

Journal

0.71

Downloadha

0.71

retty

0.69

ãģĨ

0.69

ledged

0.69

igun

0.69

ossier

0.68

vez

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.