INDEX

Explanations

specific terms related to restrictions and regulations

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

after definite articles (in various languages)

np_acts-logits-general · gemini-2.0-flash

languages and follow-ups

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Egli

-0.53

허

-0.53

 casado

-0.51

 Réponses

-0.51

 AllAfrica

-0.50

 Dirichlet

-0.50

 Aphrodite

-0.49

CString

-0.47

richlet

-0.47

 allons

-0.47

POSITIVE LOGITS

 Италијани

0.71

 Roskov

0.68

tainen

0.68

she

0.67

__))

0.67

EDEFAULT

0.66

enumii

0.66

 Ranges

0.66

boxylic

0.66

 Stadium

0.65

Activations Density 0.056%

specific terms related to restrictions and regulations

after definite articles (in various languages)

languages and follow-ups

No Comments

No Known Activations