INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Roe

-0.69

vana

-0.68

ollah

-0.68

 Kron

-0.67

ety

-0.66

UV

-0.65

 tarn

-0.65

andal

-0.65

 Sark

-0.64

 contrasted

-0.64

POSITIVE LOGITS

++

0.71

ãģ®

0.67

ãĥ¼ãĥ«

0.66

speak

0.63

Constructed

0.62

 Commons

0.62

ãĥĺãĥ©

0.61

 undead

0.61

legate

0.61

................................................................

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.