INDEX

Explanations

technical or programming-related terms, likely in a specific coding or data format

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

Cisco router configuration commands

np_acts-logits-general · gemini-2.0-flash

network configuration

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resourceCulture

-0.69

ToScroll

-0.63

RenderAtEndOf

-0.59

 Parry

-0.57

wikkeld

-0.49

 onCancelled

-0.49

 astore

-0.48

 diikuti

-0.48

SBATCH

-0.45

 καν

-0.45

POSITIVE LOGITS

 Cisco

0.79

Cisco

0.74

 router

0.71

Router

0.69

 Router

0.67

router

0.66

 routers

0.65

 Ceinture

0.63



0.62

XmlAccessType

0.61

Activations Density 0.756%

technical or programming-related terms, likely in a specific coding or data format

Cisco router configuration commands

network configuration

No Comments

No Known Activations