INDEX

Explanations

references to personal experiences and opinions in social contexts

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

after pronouns or names

np_acts-logits-general · gemini-2.0-flash

visiting places

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

PyExc

-0.59

Autoritní

-0.59

Bronnen

-0.57

amzn

-0.56

 Waray

-0.54

 initComponents

-0.53

انيف

-0.53

Хьажоргаш

-0.52

cupertino

-0.52

 hasNext

-0.51

POSITIVE LOGITS

 visits

0.83

Visiting

0.79

 visit

0.78

 Visiting

0.78

 visiting

0.74

visit

0.74

 visitation

0.73

 fréqu

0.71

 visited

0.71

 Visits

0.69

Activations Density 0.240%

references to personal experiences and opinions in social contexts

after pronouns or names

visiting places

No Comments

No Known Activations