INDEX

Explanations

phrases containing the word "of," particularly in various contexts and frequencies

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

of penis landscape regular Angela useful crochet privatized

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

PMailer

-0.27

 ComVisible

-0.26

 leaſt

-0.24

 SUDOC

-0.24

 satan

-0.24

execSQL

-0.23

 herv

-0.23

木坂

-0.23

 procès

-0.23

Irak

-0.22

POSITIVE LOGITS

GraphicsUnit

0.59

:✨

0.59

 Wonderful

0.57

دانشنامهٔ

0.57

mybatisplus

0.57

compact

0.57

essentials

0.57

 Celebrating

0.56

 AssemblyCulture

0.56

savings

0.56

Activations Density 0.020%

phrases containing the word "of," particularly in various contexts and frequencies

of penis landscape regular Angela useful crochet privatized

No Comments

No Known Activations