INDEX

Explanations

elements related to scientific terms and measurements

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

Tokens preceding quotation marks

np_acts-logits-general · gemini-2.0-flash

technical and specific units

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 tours

-0.49

mares

-0.48

meist

-0.47

 Jove

-0.46

μιουργ

-0.46

eneuve

-0.45

isObject

-0.44

ровна

-0.43

พวก

-0.43

actéristique

-0.43

POSITIVE LOGITS

QMetaType

0.69

AlterField

0.68

setVerticalGroup

0.61

 iprot

0.60

 gynhyrchwyd

0.59

 nahilalakip

0.57

المناصب

0.56

WindowConstants

0.56

sizeCache

0.56

 Roskov

0.55

Activations Density 0.733%

elements related to scientific terms and measurements

Tokens preceding quotation marks

technical and specific units

No Comments

No Known Activations