INDEX

Explanations

mathematical symbols and expressions related to various functions and structures in advanced mathematical concepts

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

code assignment

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

 disambiguazione

-0.45

Rhestr

-0.41

ustom

-0.41

enumi

-0.40

Fod

-0.40

 CanadaChoose

-0.38

Partager

-0.37

 Homer

-0.37

mara

-0.36

ousands

-0.36

POSITIVE LOGITS

enfone

0.52

舺

0.52

 postIndex

0.49

 znale

0.42

SourceChecksum

0.42

expandindo

0.41

 intStringLen

0.41

writeField

0.41

SharedDtor

0.41

PerformLayout

0.39

Activations Density 0.143%

mathematical symbols and expressions related to various functions and structures in advanced mathematical concepts

code assignment

No Comments

No Known Activations