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

ĸļ

-0.87

 Janeiro

-0.76

 Cheong

-0.74

 Archdemon

-0.72

CHAT

-0.70

 Hunters

-0.70

inas

-0.66

 Photographer

-0.65

 Whis

-0.65

 Compass

-0.64

POSITIVE LOGITS

ever

0.78

 heed

0.67

nder

0.65

 faculties

0.64

 hygiene

0.63

 eras

0.63

roph

0.61

 phases

0.61

notations

0.61

 +---

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.