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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 brakes

-0.70

geries

-0.67

 Remastered

-0.66

Mer

-0.65

 IMAGES

-0.65

clusively

-0.63

 scrolls

-0.62

 unpopular

-0.61

escription

-0.61

improve

-0.61

POSITIVE LOGITS

Vaj

0.73

icion

0.70

haw

0.68

âķĲ

0.67

zona

0.66

oster

0.66

ogh

0.65

ptive

0.65

unct

0.65

 Dame

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.