INDEX

Explanations

programming keywords and constructs related to functions and returns

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

php code fragments

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

metric

-0.40

 nahilalakip

-0.39

 transfieras

-0.38

 preuves

-0.38

 otomatig

-0.38

orate

-0.37

struts

-0.36

 Cataloging

-0.36

 betweenstory

-0.35

ftagPool

-0.35

POSITIVE LOGITS

MLLoader

0.52

yntaxException

0.47

AppMethodBeat

0.46

StoryboardSegue

0.46

'}

0.45

Atsauces

0.43

 intptr

0.42

 rumahnya

0.42

 disambiguazione

0.42

"}

0.41

Activations Density 0.007%

programming keywords and constructs related to functions and returns

php code fragments

No Comments

No Known Activations