INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 conflic

-0.88

Stretch

-0.82

 democrat

-0.81

Ħ¢

-0.78

Ĥİ

-0.78

ģ«

-0.77

itia

-0.76

 ende

-0.75

efficients

-0.73

gradation

-0.71

POSITIVE LOGITS

 mmol

0.70

ned

0.68

VI

0.67

 Number

0.65

amin

0.65

emo

0.64

iti

0.64

dB

0.62

amb

0.61

 fielded

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.