INDEX

Explanations

references to navigation-related concepts within code

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

navigation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

findpost

-0.44

CardBody

-0.42

 becauſe

-0.42

createTextNode

-0.42

DOCTYPE

-0.42

 noDo

-0.40

出版年

-0.38

BufferedWriter

-0.38

ьаж

-0.36

Datuak

-0.36

POSITIVE LOGITS

navigation

3.19

 navigation

2.02

Navigation

1.69

 Navigation

1.66

NAVIGATION

1.49

avigation

1.48

 NAVIGATION

1.45

 navigational

1.33

navig

1.30

 navegación

1.29

Activations Density 0.001%

references to navigation-related concepts within code

navigation

No Comments

No Known Activations

references to navigation-related concepts within code

navigation

No Comments

No Known Activations