INDEX

Explanations

items related to programming and schema definitions in code

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

supplementary material citations

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

 EconPapers

-0.69

 OFDb

-0.69

 MonoBehaviour

-0.62

disposing

-0.61

IndentedString

-0.59

Hozzáférés

-0.59

SharedDtor

-0.58

expandindo

-0.56

queryInterface

-0.54

 ब्रेकडाउन

-0.54

POSITIVE LOGITS

 lists

0.35

 karş

0.34

putExtra

0.34

labelledby

0.34

representing

0.33

 representing

0.33

 represents

0.33

 rappresenta

0.33

acamata

0.31

tidaknya

0.31

Activations Density 0.001%

items related to programming and schema definitions in code

supplementary material citations

No Comments

No Known Activations