INDEX

Explanations

phrases and terms related to legal penalties and punishments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 beginnetje

-0.76

IonicModule

-0.72

logger

-0.70

XmlAccessorType

-0.68

 disambiguazione

-0.66

 Leder

-0.66

adaptiveStyles

-0.66

edar

-0.65

 Rowling

-0.65

Rüyada

-0.65

POSITIVE LOGITS

 penalty

0.93

 tribute

0.93

 punishment

0.87

 penalties

0.75

 Penalty

0.72

 punishments

0.71

pun

0.68

fromCharCode

0.68

Tribute

0.65

 Punishment

0.65

Activations Density 0.051%

phrases and terms related to legal penalties and punishments

No Comments

No Known Activations