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

èĢħ

-0.83

ãĤ´

-0.82

Ã£o

-0.81

FT

-0.77

adal

-0.74

wik

-0.74

Ñı

-0.74

uary

-0.74

ãĤ¼

-0.73

ãĥŁ

-0.73

POSITIVE LOGITS

 Cran

0.72

Rye

0.69

 benchmarks

0.64

 Bones

0.63

 Hearth

0.62

 counselors

0.62

 Mesa

0.61

 Marsh

0.61

 Bone

0.61

 engagements

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.