INDEX

Explanations

significant nouns and phrases related to research findings and publications

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

examples and lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftagPool

-0.52

GEBURTSDATUM

-0.51

 FetchType

-0.49

Zeneca

-0.49

andExpect

-0.49

protoimpl

-0.47

getColumnIndex

-0.47

="@+

-0.47

 autorytatywna

-0.46

 onPostExecute

-0.45

POSITIVE LOGITS

 examples

0.73

examples

0.63

Examples

0.56

 Examples

0.55

 esempi

0.54

 eksemp

0.54

Например

0.52

 ejemplos

0.51

 exemples

0.49

 EXAMPLES

0.49

Activations Density 0.029%

significant nouns and phrases related to research findings and publications

examples and lists

No Comments

No Known Activations