INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Dwell

-0.81

 tiss

-0.74

natureconservancy

-0.70

 laun

-0.70

 tatt

-0.70

kers

-0.69

geons

-0.69

keyes

-0.69

 Annotations

-0.68

 slang

-0.66

POSITIVE LOGITS

lot

0.70

ARC

0.70

edi

0.70

 Marshall

0.68

 Axis

0.68

ideo

0.67

angle

0.66

scale

0.63

 Jordan

0.62

 Jarrett

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.