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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sake

-0.69

 delinqu

-0.65

 appliances

-0.64

enance

-0.63

 ital

-0.61

 engine

-0.60

rue

-0.59

 menu

-0.59

wip

-0.58

 table

-0.58

POSITIVE LOGITS

ļéĨĴ

0.84

ailability

0.80

 suspic

0.75

 è£ıè¦ļéĨĴ

0.73

Ô

0.72

uzzle

0.72

arger

0.71

ĺħ

0.71

itia

0.69

 Decker

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.