INDEX

Explanations

words relating to visual descriptions and sensory details

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

Light, reflection, and shine

np_acts-logits-general · gemini-2.0-flash

reflection and shine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

تقاوى

-0.77

 defaultstate

-0.76

ViewImports

-0.70

 doInBackground

-0.64

OGND

-0.63

RTLD

-0.62

mapStateToProps

-0.60

 druck

-0.60

webElementGuid

-0.58

 GeoNames

-0.58

POSITIVE LOGITS

 reflection

1.66

 reflecting

1.58

 reflect

1.55

 reflections

1.54

 reflective

1.54

 Reflect

1.49

 Reflection

1.49

 reflected

1.46

 reflects

1.45

reflect

1.40

Activations Density 0.222%

words relating to visual descriptions and sensory details

Light, reflection, and shine

reflection and shine

No Comments

No Known Activations