INDEX

Explanations

names of geographical locations and proper nouns

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

Uncommon or misspelled words

np_acts-logits-general · gemini-2.0-flash

place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

DockStyle

-0.68

reportWebVitals

-0.48

 escuchado

-0.47

PyTuple

-0.43

 informée

-0.43

 confiable

-0.42

 мәкал

-0.42

InitVars

-0.42

setVerticalGroup

-0.41

adaptiveStyles

-0.41

POSITIVE LOGITS

 village

0.54

 Village

0.51

 AttributeSet

0.49

Village

0.44

 Parish

0.43

 actionMode

0.43

village

0.42

 corti

0.40

 suburb

0.40

 Lodge

0.38

Activations Density 0.301%

names of geographical locations and proper nouns

Uncommon or misspelled words

place names

No Comments

No Known Activations