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

Zan

-0.75

 Titanic

-0.69

cos

-0.67

 Alibaba

-0.64

 Pengu

-0.63

 Jian

-0.63

 Gundam

-0.62

angible

-0.62

 Eliot

-0.62

 Nasa

-0.61

POSITIVE LOGITS

masters

0.87

SPONSORED

0.85

taboola

0.82

Reviewed

0.77

QUEST

0.74

VIEW

0.74

EGIN

0.73

REF

0.73

tails

0.72

hook

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.