INDEX

Explanations

specific references to criminal cases and legal terminology

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

relating to criminals and murderers

np_acts-logits-general · gemini-2.0-flash

criminals and offenders

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

titleMargin

-0.75

 EClass

-0.65

出版年

-0.65

AnimationsModule

-0.64

HomeAsUpEnabled

-0.62

BnF

-0.62

httphttps

-0.60

 linkovi

-0.60

ContentAsync

-0.60

ритори

-0.60

POSITIVE LOGITS

 criminals

1.17

 perpetrators

1.12

 perpetrator

1.08

 evil

1.07

 offender

1.04

 villains

1.04

 offenders

1.03

 villain

1.02

 murderer

1.02

 culprits

1.01

Activations Density 0.701%

specific references to criminal cases and legal terminology

relating to criminals and murderers

criminals and offenders

No Comments

No Known Activations