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

vernment

-0.79

 Brill

-0.76

prus

-0.68

yright

-0.67

Mub

-0.63

conserv

-0.62

eering

-0.62

 withheld

-0.61

 condemnation

-0.59

perm

-0.59

POSITIVE LOGITS

 ILCS

0.72

RNA

0.70

teenth

0.70

NX

0.68

vag

0.67

ÃįÃį

0.66

conom

0.66

 Hanson

0.66

ãĥĥãĥī

0.65

onen

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.