INDEX

Explanations

references to programming concepts and code structures

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

determine whether

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

BufferException

-0.53

ValueStyle

-0.47

IsContent

-0.46

 FileWriter

-0.45

LookAnd

-0.45

webElementXpaths

-0.44

 विश्वसनीयता

-0.42

exels

-0.41

 Normdatei

-0.40

 صوتيه

-0.40

POSITIVE LOGITS

 TestBed

0.48

 estekak

0.44

AGH

0.39

 nemlig

0.37

wości

0.36

 proves

0.36

fter

0.36

onomics

0.36

Benef

0.35

ceros

0.35

Activations Density 0.143%

references to programming concepts and code structures

determine whether

No Comments

No Known Activations