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

iro

-0.76

aminer

-0.75

 compr

-0.73

paio

-0.72

chwitz

-0.72

enhagen

-0.70

ertodd

-0.68

 suspic

-0.68

ntil

-0.66

aeda

-0.66

POSITIVE LOGITS

antine

0.76

 Tant

0.64

chem

0.64

 funer

0.61

 Stras

0.60

 discontin

0.59

Bom

0.59

 prelim

0.59

 Cart

0.58

 resh

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.