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

mite

-0.98

olitics

-0.82

irin

-0.74

sten

-0.72

olit

-0.71

mur

-0.71

meet

-0.69

Gear

-0.68

atche

-0.68

glass

-0.67

POSITIVE LOGITS

 equivalents

0.74

 indexes

0.68

 indications

0.67

 diction

0.67

OM

0.67

 initials

0.65

ĺħ

0.64

>[

0.64

 indication

0.63

 readable

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.