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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thouse

-0.66

DragonMagazine

-0.65

zynski

-0.64

Tec

-0.62

 zoning

-0.62

gregation

-0.61

 Ambro

-0.59

 hallway

-0.57

EVA

-0.57

VA

-0.57

POSITIVE LOGITS

aith

0.81

etus

0.74

rive

0.68

severe

0.66

 withd

0.66

agate

0.65

ngth

0.65

inqu

0.62

igl

0.62

irst

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.