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

yout

-0.76

LET

-0.67

 Prelude

-0.67

aby

-0.65

monster

-0.65

lyak

-0.65

 Jihad

-0.64

itches

-0.64

HAM

-0.63

 Grassley

-0.63

POSITIVE LOGITS

 related

0.69

 operated

0.65

 promoted

0.64

 associated

0.63

pri

0.63

 redes

0.62

 gamma

0.61

uchs

0.59

 affiliated

0.59

lia

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.