INDEX

Explanations

references to specific locations and organizational entities

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

structured data and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

featureID

-0.40

 diferenças

-0.39

npmjs

-0.38

 onComplete

-0.35

 actionTypes

-0.34

QMetaType

-0.34

 endregion

-0.33

="@+

-0.33

 MonoBehaviour

-0.33

 MotionEvent

-0.33

POSITIVE LOGITS

 Gotham

0.77

Gotham

0.64

limia

0.56

 CreateTagHelper

0.53

anta

0.48

 betweenstory

0.47

engar

0.47

jago

0.46

 AssemblyCulture

0.46

meliharaan

0.45

Activations Density 0.005%

references to specific locations and organizational entities

structured data and technical terms

No Comments

No Known Activations