INDEX

Explanations

references to prominent or notable figures and their achievements

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

"[Word] for [something]"

np_acts-logits-general · gemini-2.0-flash

known for something

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

rawDesc

-0.55

migrationBuilder

-0.51

 croire

-0.50

AndEndTag

-0.49

 umani

-0.48

Hochspringen

-0.48

AnchorStyles

-0.47

 prochains

-0.47

 comuniques

-0.46

 Samir

-0.45

POSITIVE LOGITS

 amongst

0.77

 among

0.74

maßen

0.70

 mundial

0.69

 contextLoads

0.68

tamment

0.68

among

0.68

 عنه

0.68

 worldwide

0.66

 своими

0.66

Activations Density 0.121%

references to prominent or notable figures and their achievements

"[Word] for [something]"

known for something

No Comments

No Known Activations