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

itton

-0.87

asca

-0.86

 agre

-0.82

¿½

-0.80

fml

-0.79

åħī

-0.79

amily

-0.76

ieu

-0.75

venants

-0.74

artisan

-0.74

POSITIVE LOGITS

 other

0.77

 Hedge

0.69

 Narendra

0.69

 bios

0.68

 otherwise

0.66

 Nare

0.63

driving

0.62

 CCTV

0.61

RSS

0.61

 Pixie

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.