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

boxing

-0.87

WOOD

-0.73

wagen

-0.73

++++

-0.72

cius

-0.71

MAC

-0.69

Pont

-0.69

nir

-0.68

PB

-0.68

earch

-0.67

POSITIVE LOGITS

 Assange

0.68

 disposition

0.67

 Hispan

0.66

sum

0.65

 hereafter

0.65

 Coulter

0.64

 mating

0.63

 entit

0.63

 Stein

0.63

 death

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.