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

 Hermione

-0.66

 EntityItem

-0.65

 Parties

-0.65

 Python

-0.65

 Debbie

-0.65

 Nadu

-0.65

 Alleg

-0.61

 Caesar

-0.60

 Gators

-0.60

 Entity

-0.60

POSITIVE LOGITS

imeter

0.79

lif

0.79

ight

0.77

ceivable

0.76

efe

0.76

 shelf

0.75

etheless

0.74

okin

0.72

manent

0.70

angible

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.