INDEX

Explanations

references to individuals or their actions related to authority or expertise

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

Follows possessive nouns

np_acts-logits-general · gemini-2.0-flash

possessives like 's

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

المناصب

-0.76

 للاسماء

-0.66

 avoient

-0.64

 yourselves

-0.62

SharedCtor

-0.61

 pouvoit

-0.61

 ThemeData

-0.61

 végétale

-0.61

 étoient

-0.59

 dedans

-0.58

POSITIVE LOGITS

 latest

0.85

 newest

0.83

0.81

']").

0.79

%");

0.73

own

0.73

%}

0.72

his

0.70

"]);

0.69

 entire

0.69

Activations Density 0.163%

references to individuals or their actions related to authority or expertise

Follows possessive nouns

possessives like 's

No Comments

No Known Activations