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

ELF

-0.69

 displeasure

-0.67

ICE

-0.64

leys

-0.63

 indict

-0.62

chlor

-0.59

ezvous

-0.59

cit

-0.59

 crews

-0.59

 Instit

-0.58

POSITIVE LOGITS

adobe

0.70

edit

0.69

Zup

0.69

sid

0.67

 Seym

0.67

 Sold

0.67

Bi

0.65

rss

0.64

owered

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.