INDEX

Explanations

attributes related to specific dimensions in a programming or markup context

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

RectangleBorder

-0.42

waitKey

-0.42

JoinColumn

-0.40

 Seeder

-0.39

पया

-0.38

JoinTable

-0.38

+#+

-0.36

BorderFactory

-0.36

rayage

-0.36

foto

-0.35

POSITIVE LOGITS

exitRule

0.51

Diweddarwch

0.51

 betweenstory

0.50

ībā

0.44

rungsseite

0.44

viewBox

0.42

EndGlobal

0.40

كويكب

0.40

 iprot

0.38

Дереккөздер

0.38

Activations Density 0.004%

attributes related to specific dimensions in a programming or markup context

<start_of_turn> user

No Comments

No Known Activations