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

grading

-0.65

alia

-0.64

jar

-0.63

 permitting

-0.63

edom

-0.61

IQ

-0.60

STER

-0.60

 Bulg

-0.60

earable

-0.59

ovych

-0.59

POSITIVE LOGITS

£ı

0.73

 Archdemon

0.71

 cents

0.70

perse

0.70

 Phant

0.69

cells

0.69

bernatorial

0.68

dq

0.67

ĸļ

0.67

quel

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.