INDEX

Explanations

mentions of live performances and events

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

the word "live"

np_acts-logits-general · gemini-2.0-flash

live events, performances, media, science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

jspx

-0.73

 typelib

-0.69

 iNdEx

-0.67

rungsseite

-0.63

مراجع

-0.63

RetentionPolicy

-0.61

}))

-0.59

 дописавши

-0.59

SpringBootTest

-0.59

 UIKit

-0.57

POSITIVE LOGITS

LIVE

0.97

 LIVE

0.92

lihood

0.90

 live

0.88

liest

0.85

 Live

0.85

Live

0.84

live

0.82

lier

0.77

wire

0.75

Activations Density 0.059%

mentions of live performances and events

the word "live"

live events, performances, media, science

No Comments

No Known Activations