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

ORTS

-0.69

Ul

-0.69

areth

-0.68

itar

-0.68

iot

-0.64

Fighting

-0.63

atsu

-0.62

Lower

-0.61

throp

-0.61

rist

-0.61

POSITIVE LOGITS

 âĸĪ

0.69

 revolving

0.65

 Chevron

0.63

 Edison

0.63

 Issa

0.63

 Lifetime

0.62

 Brill

0.61

 bulb

0.61

cov

0.61

 Kardashian

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.