INDEX

Explanations

mentions of police and official statements

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

Following a person's name, often with "said."

np_acts-logits-general · gemini-2.0-flash

he said

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PyExc

-0.55

 väli

-0.54

endregion

-0.51

 anfangen

-0.50

 geraten

-0.50

 fortsatt

-0.50

Jegyzetek

-0.49

 enää

-0.49

UserScript

-0.49

番外

-0.48

POSITIVE LOGITS

:✨

0.62

 said

0.62

 kasarigan

0.62

 ujednoznacz

0.61

UnusedPrivate

0.54

 mengatakan

0.54

\{\\

0.54

madeus

0.53

 onBind

0.53

 للاسماء

0.53

Activations Density 0.053%

mentions of police and official statements

Following a person's name, often with "said."

he said

No Comments

No Known Activations