INDEX

Explanations

references to legal concepts and proceedings

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

before prepositions or conjunctions

np_acts-logits-general · gemini-2.0-flash

completed and

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ujednoznacz

-0.52

StoryboardSegue

-0.44

zeß

-0.43

ähig

-0.43

ecap

-0.42

complexContent

-0.42

 ویکی‌پدیا

-0.41

 للمعارف

-0.41

 AspNetCore

-0.41

 continuity

-0.40

POSITIVE LOGITS

intios

0.43

 estre

0.42

esModule

0.40

 bivolt

0.39

 estavam

0.36

 Prom

0.36

("")]

0.35

cdi

0.35

Prom

0.35

 subcontra

0.35

Activations Density 0.346%

references to legal concepts and proceedings

before prepositions or conjunctions

completed and

No Comments

No Known Activations