INDEX

Explanations

references to blogs, blogging activities, and blog-related content

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

names of blogs and websites

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

hdys

-0.57

 paciencia

-0.56

uestamente

-0.54

 Jerusalén

-0.53

 Moscú

-0.53

 econó

-0.53

 comunión

-0.52

 democrática

-0.52

 antidesliz

-0.52

oció

-0.51

POSITIVE LOGITS

The

0.52

Fat

0.52

 Reel

0.47

 Nerd

0.42

 Mama

0.41

enumii

0.41

DoNot

0.41

Fru

0.40

 True

0.39

şiv

0.38

Activations Density 0.059%

references to blogs, blogging activities, and blog-related content

names of blogs and websites

No Comments

No Known Activations