INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eers

-0.86

orrow

-0.83

adden

-0.83

oola

-0.79

Attempt

-0.79

chairs

-0.78

boards

-0.76

intosh

-0.76

arton

-0.72

ummer

-0.72

POSITIVE LOGITS

Fas

0.70

itarian

0.68

 heats

0.66

Ai

0.66

 Galile

0.64

NK

0.61

 Homs

0.61

 Saber

0.59

 magnet

0.59

 Madagascar

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.