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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã±a

-0.83

advertisement

-0.75

ĸļ

-0.73

 mercy

-0.71

 Guardiola

-0.69

 GOODMAN

-0.68

azo

-0.68

ifully

-0.67

uterte

-0.66

atem

-0.66

POSITIVE LOGITS

umo

0.83

ties

0.74

lishes

0.73

XT

0.72

xt

0.72

ships

0.70

XM

0.69

conom

0.69

Bow

0.68

Cube

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.