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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Strateg

-0.72

intend

-0.67

llor

-0.67

 Towers

-0.66

 referen

-0.65

 Surviv

-0.63

essert

-0.61

 Siren

-0.60

Financial

-0.59

 Dress

-0.59

POSITIVE LOGITS

YE

0.71

aways

0.71

ulus

0.65

cy

0.65

tight

0.65

uay

0.64

RAY

0.64

way

0.63

LY

0.63

 veins

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.