INDEX

Explanations

instances of the word "add" in various contexts

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

adding elements or actions

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

PathVariable

-0.47

getHeaders

-0.46

 Fenne

-0.44

Kenzie

-0.44

ilet

-0.44

 portfolio

-0.43

 BeautifulSoup

-0.43

 RoutedEventArgs

-0.43

="#"><

-0.43

 programme

-0.42

POSITIVE LOGITS

add

1.80

ADD

1.09

Add

0.88

Add

0.82

ADD

0.72

Autoritní

0.68

Addiction

0.67

 Addiction

0.63

adds

0.63

addUser

0.61

Activations Density 0.009%

instances of the word "add" in various contexts

adding elements or actions

No Comments

No Known Activations