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

quart

-0.83

olicy

-0.81

raviolet

-0.74

insula

-0.73

assic

-0.72

rican

-0.72

andestine

-0.71

 misunder

-0.71

eric

-0.71

culated

-0.69

POSITIVE LOGITS

children

0.67

fuck

0.67

mates

0.67

ty

0.65

bug

0.64

ONSORED

0.64

 Observer

0.63

ãĤ¡

0.61

 Help

0.60

work

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.