INDEX

Explanations

occurrences of the import statement in code snippets

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

python imports

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

 âgé

-0.46

 étranger

-0.43

 occupé

-0.41

 battre

-0.40

 refusé

-0.39

 financières

-0.39

occuper

-0.39

 pleaſure

-0.39

attendre

-0.39

 foncé

-0.39

POSITIVE LOGITS

 import

1.05

 Import

0.78

import

0.77

 تضيفلها

0.66

__':

0.65

 imported

0.64

 importing

0.64

 imports

0.63

 propOrder

0.63

Import

0.62

Activations Density 0.002%

occurrences of the import statement in code snippets

python imports

No Comments

No Known Activations