INDEX

Explanations

company and product names as well as terms related to corporate entities

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

genmar kansas

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

 disambiguazione

-0.65

UnusedPrivate

-0.57

WebVitals

-0.48

[]:

-0.47

 kasarigan

-0.46

 PropertyChanged

-0.45

StructEnd

-0.45

 defaultstate

-0.45

CppMethod

-0.44

 चीज़ों

-0.44

POSITIVE LOGITS

 kapture

0.52

 skjø

0.51

libft

0.46

 kapturem

0.45

 edelstahl

0.45

 creș

0.44

fromnode

0.43

®.

0.41

 étoile

0.40

addCriterion

0.40

Activations Density 0.127%

company and product names as well as terms related to corporate entities

genmar kansas

No Comments

No Known Activations