INDEX

Explanations

structured data or specific encoding formats

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

Code snippets or program code

np_acts-logits-general · gemini-2.0-flash

code initialization and functions

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

 Biôgrafia

-0.62

ArrowToggle

-0.62

enumii

-0.58

ambut

-0.57

 kasarigan

-0.50

MLLoader

-0.50

 textStatus

-0.50

PreferredItem

-0.50

 }}"></

-0.49

GetAxis

-0.48

POSITIVE LOGITS

IntoConstraints

0.60

RegressionTest

0.59

исленность

0.59

 Accesat

0.57

GEBURTSDATUM

0.55

 Приступљено

0.54

BeginContext

0.54

 courtroom

0.53

SpringBootTest

0.53

 juiz

0.52

Activations Density 0.118%

structured data or specific encoding formats

Code snippets or program code

code initialization and functions

No Comments

No Known Activations