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

¶ħ

-0.80

pmwiki

-0.79

Downloadha

-0.74

Ĵ

-0.73

«ĺ

-0.72

HOME

-0.70

 Genie

-0.69

 Poverty

-0.69

ı

-0.69

Ī

-0.67

POSITIVE LOGITS

 probabilities

0.73

 bishop

0.69

 diagram

0.68

gui

0.68

 syndrome

0.66

baugh

0.65

lation

0.65

 sender

0.65

 receipts

0.65

 manif

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.