INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Giles

-0.80

 reel

-0.73

 Donovan

-0.72

 sergeant

-0.67

Sexual

-0.66

 shade

-0.63

 cache

-0.62

ruit

-0.62

 Romeo

-0.62

 Vaugh

-0.62

POSITIVE LOGITS

cur

0.81

seless

0.74

criptions

0.69

 slightest

0.69

cies

0.68

pec

0.67

spe

0.66

enting

0.66

lees

0.66

otal

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.