INDEX

Explanations

XPath expressions used for querying XML data

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

XML or XQuery expressions

np_acts-logits-general · gemini-2.0-flash

xpath queries

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Negative Logits

libft

-0.49

RegressionTest

-0.49

AlterField

-0.49

ignac

-0.49

agu

-0.49

 Bick

-0.45

consulté

-0.45

ודה

-0.44

zulegen

-0.43

fik

-0.43

POSITIVE LOGITS

 Roskov

0.63

 lendemain

0.58

IMPORTED

0.56

Население

0.56

jwa

0.56

ContentAlignment

0.55

PostInfinity

0.55

 relati

0.54

 ligiloj

0.54

 xpath

0.53

Activations Density 0.234%

XPath expressions used for querying XML data

XML or XQuery expressions

xpath queries

No Known Activations