INDEX

Explanations

database and coding terminology related to category management

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

Code snippets and database references

np_acts-logits-general · gemini-2.0-flash

category and identifier assignment

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

rungsseite

-0.67

 ſtate

-0.56

Efq

-0.55

 Reſ

-0.55

 utafitiHapana

-0.54

 paff

-0.53

 وتسجيلات

-0.53

 tranſ

-0.52

 تانيه

-0.52

 BIBSYS

-0.51

POSITIVE LOGITS

Personensuche

0.65

 hierarchical

0.54

 category

0.54

 Category

0.52

riction

0.51

 classification

0.51

opsida

0.51

 categor

0.50

 categories

0.50

forChild

0.50

Activations Density 0.223%

database and coding terminology related to category management

Code snippets and database references

category and identifier assignment

No Comments

No Known Activations