INDEX

Explanations

code structure elements, particularly class and method definitions

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

Code-related terms or names

np_acts-logits-general · gemini-2.0-flash

mixed language code comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

#+#

-0.65

ValueStyle

-0.58

weightedMode

-0.57

RTLR

-0.57

dafx

-0.56

GOTREF

-0.56

IntoConstraints

-0.55

HideFlags

-0.54

ftagPool

-0.52

PostInfinity

-0.51

POSITIVE LOGITS

 Audiodateien

0.47

 &___

0.43

 состо

0.42

 argint

0.40

上

0.39

 состоя

0.38

Monta

0.37

 ولي

0.37

Personensuche

0.37

ungsver

0.36

Activations Density 0.056%

code structure elements, particularly class and method definitions

Code-related terms or names

mixed language code comments

No Comments

No Known Activations