INDEX

Explanations

terms related to enforcement and legal agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

rettes

-0.57

🇴

-0.57

 numberOfRows

-0.56

躇

-0.56

nergie

-0.55

útil

-0.54

 poveznice

-0.52

lotte

-0.52

óbal

-0.51

categorized

-0.50

POSITIVE LOGITS

 enforced

0.88

 enforcing

0.84

 enforce

0.82

 enforcement

0.76

enforcement

0.73

 enforceable

0.73

 upheld

0.69

+#+#

0.69

 adherence

0.68

enforce

0.68

Activations Density 0.286%

terms related to enforcement and legal agreements

No Comments

No Known Activations