INDEX

Explanations

references to programming or scripting language functionality

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

Code snippets or non-English vocabulary

np_acts-logits-general · gemini-2.0-flash

mathematical variables and commands

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

 transfieras

-0.61

 Majefty

-0.54

 kasarigan

-0.54

internalType

-0.54

 magnes

-0.53

 CURIAM

-0.52

ſelf

-0.51

complexContent

-0.51

 Taktlose

-0.51

 الحره

-0.50

POSITIVE LOGITS

 offiziellen

0.33

asnya

0.32

 Zufall

0.32

Referenties

0.32

 Gehalt

0.31

owano

0.31

 Dichtung

0.31

 vergüenza

0.31

 discursos

0.31

šiť

0.31

Activations Density 0.454%

references to programming or scripting language functionality

Code snippets or non-English vocabulary

mathematical variables and commands

No Comments

No Known Activations