INDEX

Explanations

incidents related to legal enforcement or conflict situations

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

Physical altercations and violence

np_acts-logits-general · gemini-2.0-flash

physical violence and assault

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 فريبيس

-0.81

 Audiodateien

-0.57

Viitteet

-0.57

URLException

-0.57

WriteTagHelper

-0.53

 informat

-0.53

AccessorTable

-0.53

Tembelea

-0.53

Drying

-0.52

ψ

-0.51

POSITIVE LOGITS

 fists

1.12

 punches

1.06

 altercation

1.03

 violence

1.02

 brawl

1.01

 fist

1.00

 punched

0.96

 assault

0.96

 fights

0.94

 punching

0.94

Activations Density 0.358%

incidents related to legal enforcement or conflict situations

Physical altercations and violence

physical violence and assault

No Comments

No Known Activations