INDEX

Explanations

mentions of input parameters or functions in programming contexts

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

SHALL THE

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

 renamed

-0.49

sepeda

-0.44

 برانيه

-0.43

jangkau

-0.41

 Daarna

-0.41

RouterModule

-0.40

 tertawa

-0.40

 Aún

-0.40

 nahilalakip

-0.40

 RouterModule

-0.39

POSITIVE LOGITS

 وتسجيلات

0.57

UnusedPrivate

0.53

PreferredItem

0.48

 corner

0.48

InjectAttribute

0.47

featureID

0.47

 AssemblyTitle

0.47

Portail

0.46

 ExecuteAsync

0.45

 Associ

0.45

Activations Density 0.001%

mentions of input parameters or functions in programming contexts

SHALL THE

No Comments

No Known Activations