INDEX

Explanations

references to object-oriented programming concepts, specifically related to class attributes and methods

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

self. or this. member access

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

 дописавши

-0.45

AndroidJUnit

-0.44

تقاوى

-0.42

httphttps

-0.41

 AssemblyTitle

-0.41

 ivelany

-0.39

 الحره

-0.36

TagMode

-0.35

ftagPool

-0.35

utilisons

-0.34

POSITIVE LOGITS

awtextra

0.49

GIVEREF

0.45

antidad

0.45

⬧

0.44

 DBNull

0.44

Volker

0.43

 Kirchner

0.42

WebVitals

0.42

 Ilha

0.42

 Hesse

0.42

Activations Density 1.192%

references to object-oriented programming concepts, specifically related to class attributes and methods

self. or this. member access

No Comments

No Known Activations