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

typ

-0.68

 typical

-0.66

Ĥ¬

-0.66

VERSION

-0.63

ETH

-0.63

UCK

-0.63

 Codec

-0.63

INAL

-0.62

erer

-0.61

////////////////

-0.61

POSITIVE LOGITS

enegger

0.77

tarians

0.74

enza

0.72

 collided

0.71

 overlap

0.71

bish

0.69

aminer

0.68

 clashed

0.67

 illum

0.67

peria

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.