INDEX

Explanations

code snippets related to data handling in spreadsheets

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

list manipulation

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Autoritní

-0.65

 defStyleAttr

-0.63

Hentet

-0.61

 հղումներ

-0.61

 CreateTagHelper

-0.59

 يتيمه

-0.57

Personendaten

-0.52

PostMapping

-0.51

 HomeController

-0.51

rungsseite

-0.50

POSITIVE LOGITS

 aufnehmen

0.41

kuuta

0.40

 Constitucional

0.39

StoredProcedure

0.39

 comigo

0.39

 join

0.38

join

0.38

 lepas

0.35

 joining

0.35

WillAppear

0.35

Activations Density 0.132%

code snippets related to data handling in spreadsheets

list manipulation

No Comments

No Known Activations