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

 Ferdinand

-0.68

-0.67

 Ludwig

-0.62

 Stephens

-0.61

 Luxembourg

-0.60

 Walton

-0.60

 taxed

-0.58

 Hague

-0.58

 Kaine

-0.57

 Perkins

-0.56

POSITIVE LOGITS

umbn

0.81

ipment

0.80

¥µ

0.77

Installation

0.75

lished

0.75

iri

0.73

Photos

0.72

Gaza

0.72

liest

0.71

Rating

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.