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

 Diet

-0.66

edition

-0.62

din

-0.61

 Jong

-0.59

mun

-0.59

 stiff

-0.58

 heated

-0.58

andum

-0.57

 Revised

-0.57

ãħĭãħĭ

-0.56

POSITIVE LOGITS

icter

0.86

WAYS

0.73

tower

0.71

 Mermaid

0.71

ovo

0.69

 Killing

0.69

 Paladin

0.69

bg

0.69

VPN

0.69

folk

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.