INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

olar

-0.73

AME

-0.71

itized

-0.70

SS

-0.70

 SHARES

-0.65

 Appl

-0.65

strip

-0.63

pha

-0.63

ually

-0.63

native

-0.62

POSITIVE LOGITS

 Farage

0.81

pse

0.80

\\\\\\\\

0.73

 Erdogan

0.68

 Biden

0.66

iciary

0.66

į

0.65

 Russo

0.65

 Jensen

0.64

oÄŁ

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.