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

ãĥīãĥ©

-0.84

ãĤ¦ãĤ¹

-0.84

Wi

-0.72

éĽ

-0.72

ãĥİ

-0.70

anism

-0.69

 Horus

-0.67

Nau

-0.67

ideo

-0.66

waves

-0.66

POSITIVE LOGITS

cit

0.88

cific

0.86

ocument

0.68

 audits

0.64

efully

0.64

aciously

0.64

 blob

0.62

 clipboard

0.61

 proble

0.60

earch

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.