INDEX

Explanations

comments and documentation in code

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

Code comments and license information

np_acts-logits-general · gemini-2.0-flash

comment markers followed by descriptive words

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

awtextra

-0.72

arangay

-0.68

ſcher

-0.64

tinyos

-0.63

UrlResolution

-0.63

 Italijanski

-0.63



-0.62

 betweenstory

-0.59

Diweddarwch

-0.58

----</

-0.57

POSITIVE LOGITS

New

0.42

//

0.41

The

0.41

0.40

/*

0.39

com

0.39

Options

0.39

Activations Density 0.083%

comments and documentation in code

Code comments and license information

comment markers followed by descriptive words

No Comments

No Known Activations