INDEX

Explanations

references to configuration and settings within technical documentation or code

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

Configuration settings or preferences

np_acts-logits-general · gemini-2.0-flash

application settings options

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

tvguidetime

-0.71

BufferException

-0.64

 AssemblyCompany

-0.60

 StatefulWidget

-0.59

GIVEREF

-0.58

 AdapterView

-0.55

 AppColors

-0.55

 AssemblyProduct

-0.55

ConstraintMaker

-0.55

findpost

-0.55

POSITIVE LOGITS

 settings

0.90

 Settings

0.79

SETTINGS

0.79

settings

0.75

Settings

0.74

 setting

0.71

urator

0.70

 Setting

0.70

 SETTING

0.68

setting

0.66

Activations Density 0.119%

references to configuration and settings within technical documentation or code

Configuration settings or preferences

application settings options

No Comments

No Known Activations