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

mons

-0.82

ilion

-0.82

 Lives

-0.70

emetery

-0.69

dos

-0.68

enced

-0.67

celona

-0.67

schild

-0.66

emis

-0.66

 Jaguar

-0.66

POSITIVE LOGITS

isin

0.82

ube

0.76

anut

0.72

 aggregation

0.68

 wraps

0.66

ince

0.66

Rih

0.65

 Kardash

0.64

 renegoti

0.64

 peanut

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.