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

atron

-0.84

lette

-0.76

dt

-0.71

factor

-0.71

arette

-0.68

entity

-0.67

 Lone

-0.67

horse

-0.65

Walker

-0.65

roth

-0.64

POSITIVE LOGITS

etheless

0.74

ĺħ

0.68

 foregoing

0.67

 peacefully

0.67

 satisf

0.64

 pressing

0.64

alty

0.63

 earnest

0.62

 peaceful

0.61

 mutually

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.