INDEX

Explanations

specific items or ingredients mentioned within a recipe or cooking context

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

Followed by common words ("the", "a", etc.)

np_acts-logits-general · gemini-2.0-flash

just followed by a word

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OrBuilder

-0.47

 AspNetCore

-0.44

الحياه

-0.44

BitConverter

-0.43

ngdoc

-0.42

jsxFileName

-0.41

Pranala

-0.40

BeginContext

-0.40

 ExecuteAsync

-0.40

 ReactDOM

-0.39

POSITIVE LOGITS

VersionUID

0.40

 gemeint

0.39

orthand

0.38

falgar

0.38

 meant

0.37

dehyde

0.37

 الشه

0.37

 famous

0.36

MENAFN

0.36

ceros

0.35

Activations Density 0.662%

specific items or ingredients mentioned within a recipe or cooking context

Followed by common words ("the", "a", etc.)

just followed by a word

No Comments

No Known Activations