INDEX

Explanations

code elements and structure commonly used in programming languages or markup languages

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

Code related to registries or configuration

np_acts-logits-general · gemini-2.0-flash

technical terms after delimiters

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

 Shakspeare

-0.76

 Shaksp

-0.76

 Pamph

-0.76

 Phono

-0.74

 Pyramids

-0.71

 Hymns

-0.71

 zirc

-0.70

 sherds

-0.70

 limestones

-0.70

 holog

-0.69

POSITIVE LOGITS

Men

0.60

Are

0.58

 More

0.56

him

0.55

Far

0.54

Et

0.54

La

0.54

Be

0.53

 Most

0.53

 Не

0.53

Activations Density 0.684%

code elements and structure commonly used in programming languages or markup languages

Code related to registries or configuration

technical terms after delimiters

No Comments

No Known Activations