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

 Tinker

-0.74

 dwarves

-0.67

 Dwar

-0.65

 Fischer

-0.62

ONSORED

-0.62

correct

-0.62

 Gleaming

-0.62

 rigged

-0.61

Reviewer

-0.61

eful

-0.61

POSITIVE LOGITS

 Asia

2.04

Asia

1.32

 Memorial

1.06

 Asian

0.96

aram

0.87

 Panama

0.81

 Manila

0.79

 Americas

0.71

Asian

0.71

Japan

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.