INDEX

Explanations

Java import statements and associated code components

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

<start_of_turn>user

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

 ujednoznacz

-0.58

sizeCache

-0.47

EDEFAULT

-0.46

AutoField

-0.41

rungsseite

-0.38

Tikang

-0.38

adaptiveStyles

-0.35

formik

-0.34

новниш

-0.34

 zůst

-0.34

POSITIVE LOGITS

BeginInit

0.55

MockBean

0.52

 COLLECT

0.50

 priest

0.49

 Printer

0.48

ranes

0.48

Clan

0.48

 Vaccine

0.47

 Spin

0.47

 auffi

0.47

Activations Density 0.001%

Java import statements and associated code components

<start_of_turn>user

No Comments

No Known Activations