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

ļéĨĴ

-0.82

iful

-0.76

oried

-0.71

quished

-0.70

agame

-0.69

ishes

-0.69

umerable

-0.69

 Journals

-0.68

 Gleaming

-0.67

 NASL

-0.66

POSITIVE LOGITS

memory

0.67

alias

0.65

 veget

0.65

 eaves

0.62

Rah

0.62

croft

0.62

pay

0.61

nb

0.60

church

0.60

bey

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.