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

OTAL

-0.64

ennes

-0.64

algia

-0.63

èĢħ

-0.63

AME

-0.62

EMA

-0.61

Filename

-0.61

ACH

-0.60

BuyableInstoreAndOnline

-0.60

POSITIVE LOGITS

itionally

0.71

iband

0.71

jriwal

0.71

ndra

0.71

lain

0.68

::::

0.67

isal

0.67

issance

0.66

lance

0.66

rences

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.