INDEX

Explanations

discussions about legal defenses and rights, particularly in relation to child abuse material and justifications for possession or distribution

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

text describing legal defenses and justifications for possessing or distributing illegal content.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 propOrder

-0.36

 Neglect

-0.34

zbęd

-0.32

 tủ

-0.32

 caché

-0.31

 змі

-0.31

 fortes

-0.31

 éter

-0.30

 impatient

-0.30

 additional

-0.30

POSITIVE LOGITS

 legitimate

1.63

 harmless

1.45

 lawful

1.40

 innocent

1.37

 legitimately

1.36

innocent

1.30

 legit

1.30

 innocently

1.28

 lawfully

1.27

 innoc

1.23

Activations Density 1.261%

discussions about legal defenses and rights, particularly in relation to child abuse material and justifications for possession or distribution

text describing legal defenses and justifications for possessing or distributing illegal content.

No Comments

No Known Activations