INDEX

Explanations

parameters and options related to programming functions or methods

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

parameters and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

delwed

-0.53

SharedCtor

-0.47

তথ্যসূত্র

-0.43

featureID

-0.42

 betweenstory

-0.39

astify

-0.38

CloseOperation

-0.38

'{@

-0.37

+#+

-0.35

/***/

-0.35

POSITIVE LOGITS

putAll

0.53

setArguments

0.48

urlencoded

0.48

alimentation

0.47

 confounding

0.45

 tariffs

0.44

 alimentaire

0.44

 options

0.44

laubt

0.44

ujan

0.44

Activations Density 0.089%

parameters and options related to programming functions or methods

parameters and arguments

No Comments

No Known Activations