INDEX

Explanations

multiple instances of specific tokens or numbers

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

Times in "hour:minutes" format

np_acts-logits-general · gemini-2.0-flash

dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ngdoc

-0.68

MigrationBuilder

-0.56

krut

-0.53

 &___

-0.52

 AssemblyCulture

-0.52

 protoimpl

-0.51

 Numerade

-0.50

ładka

-0.47

 tartalomajánló

-0.47

綜合報導

-0.47

POSITIVE LOGITS

 midnight

0.76

 initComponents

0.65

midnight

0.62

 MainAxisSize

0.57

gebraucht

0.54

 Midnight

0.53

 Strawberries

0.52

windowFixed

0.51

 noon

0.51

makeConstraints

0.51

Activations Density 0.063%

multiple instances of specific tokens or numbers

Times in "hour:minutes" format

dates and times

No Comments

No Known Activations