INDEX

Explanations

statements of acknowledgement or addition in discussions

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

"added" or its foreign translations

np_acts-logits-general · gemini-2.0-flash

adding to a statement

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.82

webElementXpaths

-0.73

 ✭✭

-0.63

 يتيمه

-0.58

transQ

-0.58

DockStyle

-0.57

 мәкал

-0.57

حياتها

-0.57

 againſt

-0.56

 queſta

-0.54

POSITIVE LOGITS

 añadió

0.55

 added

0.52

 añade

0.50

وأضاف

0.47

 agregó

0.45

 añadido

0.43

 ajouté

0.43

added

0.42

 añad

0.42

 adds

0.42

Activations Density 0.102%

statements of acknowledgement or addition in discussions

"added" or its foreign translations

adding to a statement

No Comments

No Known Activations

statements of acknowledgement or addition in discussions

"added" or its foreign translations

adding to a statement

No Comments

No Known Activations