INDEX

Explanations

terms related to legal governance and permissions

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

governing permissions

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

writeFieldEnd

-0.68

VYMaps

-0.66

 AssemblyTitle

-0.65

 ChromeDriver

-0.65

 uLocal

-0.64

ThroughAttribute

-0.62

WebServlet

-0.61

 varargin

-0.61

HasAnnotation

-0.61

########.

-0.59

POSITIVE LOGITS

://$

0.52

EMPL

0.45

 Económica

0.44

 libremente

0.44

 Formación

0.41

 Relaciones

0.41

Données

0.41

 Matériau

0.40

ModelMap

0.40

ærer

0.40

Activations Density 0.001%

terms related to legal governance and permissions

governing permissions

No Comments

No Known Activations

terms related to legal governance and permissions

governing permissions

No Comments

No Known Activations