INDEX

Explanations

references to platform-related terminology in technical documentation

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

platform

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

transQ

-0.60

toHaveBeenCalled

-0.49

//

-0.48

fromnode

-0.44

aktery

-0.44

XmlAccessorType

-0.44

 ervoor

-0.44

 creatively

-0.44

 hijau

-0.42

crollView

-0.42

POSITIVE LOGITS

platform

1.34

 platform

1.09

 Platform

0.95

Platform

0.93

 platforms

0.92

platforms

0.88

PLATFORM

0.84

 PLATFORM

0.83

平台

0.83

 Platforms

0.81

Activations Density 0.000%

references to platform-related terminology in technical documentation

platform

No Comments

No Known Activations