INDEX

Explanations

programming language structures and keywords related to class inheritance and interfaces

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

starts with <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

 Meksiku

-0.69

UserScript

-0.57

protoimpl

-0.54

 bParam

-0.53

tanleria

-0.52

 mergeFrom

-0.51

MarshalTo

-0.48

prepareStatement

-0.48

 Fenn

-0.48

тистика

-0.48

POSITIVE LOGITS

CloseOperation

0.50

">//

0.40

contentLoaded

0.35

RepeatedField

0.35

 rând

0.32

SupportActionBar

0.31

randomUUID

0.31

 assurent

0.31

Ҭ

0.30

crumb

0.29

Activations Density 0.000%

programming language structures and keywords related to class inheritance and interfaces

starts with <start_of_turn>user

No Comments

No Known Activations