INDEX

Explanations

mathematical expressions and notations related to statistics or data analysis

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

division by 2

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

Демографія

-0.54

BagConstraints

-0.50

Referanser

-0.49

 Oper

-0.47

 climber

-0.47

 AssemblyCompany

-0.46

 vocales

-0.46

 opérateur

-0.44

tonsoft

-0.43

Personensuche

-0.43

POSITIVE LOGITS

 نصف

0.52

 незавершена

0.50

half

0.46

Half

0.46

 half

0.43

 Hälfte

0.42

 HALF

0.42

HALF

0.41

GenerationType

0.40

 halve

0.39

Activations Density 0.137%

mathematical expressions and notations related to statistics or data analysis

division by 2

No Comments

No Known Activations