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

 Marina

-0.68

 Vern

-0.65

 Transparency

-0.64

 Magnum

-0.64

 Boxing

-0.63

PT

-0.62

 Claude

-0.62

Tec

-0.61

 Alberto

-0.61

Dj

-0.61

POSITIVE LOGITS

çīĪ

0.97

luaj

0.87

ð

0.81

edin

0.79

İĭ

0.78

awar

0.77

00200000

0.77

rast

0.74

izons

0.74

utsch

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.