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

Null

-0.69

apore

-0.69

eca

-0.68

IX

-0.67

 Dynasty

-0.67

oqu

-0.67

 Chin

-0.67

acea

-0.65

Sty

-0.65

cheon

-0.64

POSITIVE LOGITS

 conclud

0.89

 confir

0.76

 referen

0.71

ITNESS

0.69

database

0.64

LIB

0.64

 Migration

0.63

 newsp

0.62

 mathemat

0.62

 intrins

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.