INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ascus

-0.68

Suc

-0.68

rite

-0.65

emonic

-0.64

 Thorn

-0.64

icz

-0.63

 Presbyter

-0.63

gement

-0.63

Pok

-0.62

ibility

-0.60

POSITIVE LOGITS

osate

0.78

washer

0.75

 showc

0.68

Īè

0.68

Bott

0.68

Ĥİ

0.66

ģ«

0.65

cean

0.65

\\\\

0.64

 Royale

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.