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

 toile

-0.78

stood

-0.77

jah

-0.75

 detainees

-0.71

buster

-0.69

quartered

-0.64

thouse

-0.64

tan

-0.63

SourceFile

-0.63

ures

-0.61

POSITIVE LOGITS

 Spears

0.74

 Empires

0.70

ciation

0.69

abil

0.69

 Addiction

0.68

liam

0.67

aunt

0.67

icated

0.67

 Grave

0.67

ABLE

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.