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

terday

-0.73

 Kemp

-0.72

zees

-0.64

hero

-0.64

icians

-0.64

 herald

-0.62

crow

-0.62

bear

-0.62

robe

-0.61

Kol

-0.60

POSITIVE LOGITS

perty

0.69

itol

0.67

izu

0.67

arbon

0.65

 quot

0.64

headers

0.64

 Divide

0.64

 largeDownload

0.62

algia

0.60

okin

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.