INDEX

Explanations

proper nouns, specifically names and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Initials before names

np_acts-logits-general · gemini-2.0-flash

names of people

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.70

✨:

-0.68

qrstuvwxyz

-0.53

OGND

-0.53

myapplication

-0.50

 Hauptstadt

-0.48

findpost

-0.47

 textStatus

-0.47

setVerticalGroup

-0.46

 défendre

-0.46

POSITIVE LOGITS

 invokingState

0.63

teve

0.52

archiviato

0.52

__*/

0.51

 Danh

0.49

trick

0.48

тьяна

0.48

 stub

0.47

ρίς

0.47

Ouv

0.47

Activations Density 0.257%

proper nouns, specifically names and organizations

Initials before names

names of people

No Comments

No Known Activations