INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ileaks

-0.78

 comprom

-0.77

agne

-0.76

vae

-0.75

aign

-0.75

lio

-0.75

aye

-0.74

ality

-0.69

vere

-0.69

redo

-0.67

POSITIVE LOGITS

API

0.71

BS

0.70

MS

0.65

SL

0.64

 Xbox

0.63

 Achievements

0.63

KP

0.62

MS

0.62

KK

0.62

CV

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.