INDEX

Explanations

references to characters and their roles in narratives

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

after conjunctions or prepositions

np_acts-logits-general · gemini-2.0-flash

names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

•Literature

references to characters and their roles in narratives

No Comments

Negative Logits

########.

-0.77

+#+#

-0.71

Hochspringen

-0.69

retudo

-0.69

 saveiro

-0.67

AxisAlignment

-0.67

 ſever

-0.66

 étoient

-0.65

 Bleach

-0.65

примеча

-0.65

POSITIVE LOGITS

 ExecuteAsync

0.53

 Normdatei

0.52

 Coach

0.52

Mr

0.52

Dr

0.50

AntiForgeryToken

0.47

министра

0.47

0.46

 Officer

0.45

ברת

0.45

Activations Density 0.280%

references to characters and their roles in narratives

after conjunctions or prepositions

names and titles

No Comments

No Known Activations