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

psey

-0.93

ichick

-0.81

rison

-0.81

ascript

-0.81

ificant

-0.79

ppard

-0.78

ificantly

-0.78

isphere

-0.76

ilater

-0.76

escription

-0.74

POSITIVE LOGITS

Kod

0.83

 Naval

0.77

Mol

0.76

 Rivals

0.75

 Warfare

0.75

 Rarity

0.73

 Hilton

0.71

ä»£

0.71

 Laksh

0.70

Pri

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.