INDEX

Explanations

phrases related to unlimited access and options

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

unlimited

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

bootstrapcdn

-0.62

 дописавши

-0.59

 فريبيس

-0.57



-0.55

VolleyError

-0.51

Personendaten

-0.51

 useAppContext

-0.51

новништво

-0.51

AnchorTagHelper

-0.50

FormTagHelper

-0.50

POSITIVE LOGITS

 unlimited

0.56

 ilimit

0.56

Unlimited

0.51

 Unlimited

0.44

 inexhaustible

0.43

 endless

0.43

unlimited

0.41

 forever

0.40

 impunity

0.40

 limitless

0.39

Activations Density 0.015%

phrases related to unlimited access and options

unlimited

No Comments

No Known Activations