INDEX

Explanations

code comments and import statements in programming documents

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

importing code

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

 snippetHide

-0.70

InSection

-0.51

]=>

-0.50

WaitGroup

-0.49

 ModelRenderer

-0.47

SharedDtor

-0.46

onViewCreated

-0.45

 Italijani

-0.45

Carriera

-0.45

➯

-0.45

POSITIVE LOGITS

interopRequire

0.48

 allies

0.48

import

0.43

alism

0.42

 import

0.39

InternalFrame

0.39

XDECREF

0.38

 rocks

0.38

 glassware

0.38

 Sing

0.38

Activations Density 0.002%

code comments and import statements in programming documents

importing code

No Comments

No Known Activations