INDEX

Explanations

entities and their associated attributes or relationships in structured data

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

Prepositions and symbols

np_acts-logits-general · gemini-2.0-flash

Mac Android/iOs

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

â

-0.88

Â

-0.78

AndEndTag

-0.75

Â

-0.73

â

-0.68

‚

-0.60

…

-0.58

hasOwnProperty

-0.56

::_('

-0.56

-0.55

POSITIVE LOGITS

 poveznice

0.63

Personensuche

0.63

MarshalTo

0.62

UserScript

0.62

satunya

0.60

RTEE

0.59

 Biôgrafia

0.58

astify

0.58

 otomatig

0.57

下载附件

0.55

Activations Density 1.734%

entities and their associated attributes or relationships in structured data

Prepositions and symbols

Mac Android/iOs

No Comments

No Known Activations