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

pes

-0.72

 lime

-0.65

earances

-0.65

 dollar

-0.62

 mism

-0.62

 fasc

-0.62

 unequ

-0.62

 Masonic

-0.61

unta

-0.59

displayText

-0.59

POSITIVE LOGITS

gren

0.70

stown

0.67

aceous

0.65

raviolet

0.65

Walker

0.64

chester

0.62

actor

0.61

ellation

0.61

assis

0.60

 Dragonbound

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.