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

otte

-0.79

angu

-0.77

ivating

-0.70

opian

-0.68

 yourselves

-0.68

iven

-0.67

.)

-0.66

ope

-0.65

ogen

-0.63

 cour

-0.63

POSITIVE LOGITS

--------------------------------------------------------

0.83

Reviewer

0.81

ufact

0.79

SourceFile

0.77

Textures

0.77

UTERS

0.76

DD

0.76

Ô

0.75

cffff

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.