INDEX

Explanations

code related to database structures and identifiers

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

"id" or "ID" labels

np_acts-logits-general · gemini-2.0-flash

unique identifier keys

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gepubliceerd

-0.68

цездатний

-0.60

oa̍t

-0.59

Statistiche

-0.59

 monotonous

-0.58

 internetowa

-0.58

FetchType

-0.57

sendFile

-0.56

енча

-0.54

idhi

-0.53

POSITIVE LOGITS

glGen

0.69

Hentet

0.58

 useParams

0.56

 Demp

0.54

唯一

0.53

 numbering

0.52

Serializable

0.50

Unique

0.50

INSEE

0.49

 ISNI

0.49

Activations Density 0.574%

code related to database structures and identifiers

"id" or "ID" labels

unique identifier keys

No Comments

No Known Activations