INDEX

Explanations

quantitative comparisons and classifications within a given context

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

Followed by a number, especially two or three

np_acts-logits-general · gemini-2.0-flash

classifying numbers or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 AssemblyTitle

-0.65

Personendaten

-0.48

 endfor

-0.46

 chiar

-0.45

ItemLayout

-0.45

 transfieras

-0.45

Hozzáférés

-0.45

पया

-0.44

 useAppContext

-0.44

adaptiveStyles

-0.44

POSITIVE LOGITS

two

1.69

 three

1.63

两种

1.45

三种

1.41

two

1.38

兩種

1.37

 four

1.32

 trois

1.31

 deux

1.30

three

1.29

Activations Density 0.787%

quantitative comparisons and classifications within a given context

Followed by a number, especially two or three

classifying numbers or quantities

No Comments

No Known Activations