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

inge

-0.81

MLA

-0.68

 burner

-0.67

lie

-0.62

optim

-0.61

 achie

-0.61

itto

-0.60

 trembling

-0.59

 boil

-0.59

ettle

-0.59

POSITIVE LOGITS

Ruk

0.61

ouf

0.59

Louis

0.58

isphere

0.58

 Marian

0.57

igated

0.57

achusetts

0.57

schild

0.57

cca

0.56

########

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.