INDEX

Explanations

subject matter related to detailed descriptions and analyses, particularly focusing on components and characteristics

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

after common punctuation

np_acts-logits-general · gemini-2.0-flash

causality, rookie, having, indicated

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

 Administrativna

-0.60

 &___

-0.52

UserScript

-0.48

transQ

-0.47

Παραπομπές

-0.44

どうしても

-0.42

DoubleQuotes

-0.41

 utafitiHapana

-0.41

يكب

-0.40

Collegamenti

-0.39

POSITIVE LOGITS

CloseOperation

0.57

 discorso

0.52

 članak

0.46

EndInit

0.45

signol

0.44

entum

0.44

ChildScrollView

0.44

Hair

0.42

 zijne

0.41

PyExc

0.40

Activations Density 0.495%

subject matter related to detailed descriptions and analyses, particularly focusing on components and characteristics

after common punctuation

causality, rookie, having, indicated

No Comments

No Known Activations