INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

icip

-0.73

escap

-0.72

peat

-0.68

alion

-0.66

esthesia

-0.66

ivari

-0.65

anchester

-0.65

cin

-0.64

cu

-0.64

erva

-0.64

POSITIVE LOGITS

gon

0.76

 Neph

0.60

ails

0.59

 Laboratories

0.57

igmat

0.57

 shave

0.56

å§«

0.56

 confir

0.55

 blunt

0.55

æĸ¹

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.