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

osuke

-0.68

ocious

-0.68

guyen

-0.68

 sibling

-0.66

 disorder

-0.66

 brother

-0.64

 Messiah

-0.64

anguage

-0.63

 TheNitromeFan

-0.63

 blight

-0.63

POSITIVE LOGITS

ãĤ¡

0.75

ilib

0.69

 VIDE

0.66

bid

0.66

 Emin

0.65

ERAL

0.65

Sec

0.65

SG

0.64

Priv

0.64

 ----------------------------------------------------------------

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.