INDEX

Explanations

terms related to legal and medical contexts of wrongdoing and standards of care

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

illegal, breach, excessive, irrational

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

RegistryLite

-0.46

 Савезне

-0.41

skraft

-0.38

InjectMocks

-0.36

haikusbot

-0.36

 deleteById

-0.35

enumii

-0.34

aphne

-0.34

på

-0.34

 hozzá

-0.34

POSITIVE LOGITS

 itinéraires

0.48

 AspNetCore

0.45

unteer

0.42

ChildScrollView

0.41

Joi

0.41

istible

0.41

zcze

0.40

addCriterion

0.40

ruptedException

0.40

LayoutConstraint

0.40

Activations Density 0.193%

terms related to legal and medical contexts of wrongdoing and standards of care

illegal, breach, excessive, irrational

No Comments

No Known Activations