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

©¶æ

-0.81

»Ĵ

-0.67

 Wrestle

-0.66

 confir

-0.65

 fert

-0.64

ossier

-0.62

 tradem

-0.62

 Hispan

-0.62

etheless

-0.61

 Hitman

-0.59

POSITIVE LOGITS

coded

0.83

artments

0.82

 digits

0.82

locks

0.76

items

0.74

bucks

0.73

Discussion

0.72

phabet

0.71

orian

0.70

Comments

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.