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

axter

-0.82

etsy

-0.74

dit

-0.69

Ware

-0.68

ebin

-0.68

ocking

-0.65

rig

-0.64

iver

-0.64

ayne

-0.63

onne

-0.62

POSITIVE LOGITS

 DEFENSE

0.67

iannopoulos

0.66

 Kosovo

0.65

ufact

0.65

pan

0.64

ctors

0.64

abs

0.64

 Slovenia

0.63

 Mecca

0.63

 Warsaw

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.