INDEX

Explanations

patterns related to scientific experiments and data analysis

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

mathematical expressions

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

UserScript

-0.47

 himo

-0.46

 MainAxisSize

-0.42

Gez

-0.41

/*

-0.40

CreateIndex

-0.38

 disponibilités

-0.37

 NavController

-0.37

tableFuture

-0.36

 gynhyrchwyd

-0.36

POSITIVE LOGITS

Personensuche

0.65

Personendaten

0.55

webElementXpaths

0.46

 '\\;'

0.46

GIVEREF

0.44

énario

0.44

Tembelea

0.43

Rohy

0.41

BeginContext

0.40

retweeted

0.40

Activations Density 0.013%

patterns related to scientific experiments and data analysis

mathematical expressions

No Comments

No Known Activations