INDEX

Explanations

the usage of the term "list" in various contexts related to retrieving data

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

listing

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

bcryptjs

-0.53

Luc

-0.51

HtmlAttribute

-0.50

tagHelperRunner

-0.48

новништво

-0.42

bcrypt

-0.42

 betweenstory

-0.41

bows

-0.40

burns

-0.40

alds

-0.40

POSITIVE LOGITS

 насељу

0.50

 kasarigan

0.49

NameInMap

0.48

 listado

0.46

 powierzch

0.46

OrWhiteSpace

0.45

 hombro

0.45

 anniversaire

0.43

 classify

0.42

 Lijst

0.42

Activations Density 0.006%

the usage of the term "list" in various contexts related to retrieving data

listing

No Comments

No Known Activations