INDEX

Explanations

terms related to legal disclaimers and user information management

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

Followed by "at" or "by"

np_acts-logits-general · gemini-2.0-flash

at any time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

SharedCtor

-0.73

GEBURTS

-0.65

ValueStyle

-0.61

HideFlags

-0.59

脚注の使い方

-0.58

хьтан

-0.57

참고

-0.56

Autoritní

-0.56

Diweddarwch

-0.54

nec

-0.53

POSITIVE LOGITS

 anytime

1.16

 jederzeit

1.00

随时

0.94

隨時

0.87

 Anytime

0.78

Anytime

0.77

いつでも

0.66

any

0.65

 kapan

0.59

 любое

0.59

Activations Density 0.312%

terms related to legal disclaimers and user information management

Followed by "at" or "by"

at any time

No Comments

No Known Activations