INDEX

Explanations

references to variables or parameters in mathematical expressions

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 '\\;'

-0.49

crollView

-0.49

Diweddarwch

-0.44

蚪

-0.44

QLabel

-0.44

 referrerpolicy

-0.43

 dAtA

-0.43

 multivariate

-0.43

MouseAdapter

-0.43

—

-0.42

POSITIVE LOGITS

Bodies

0.56

 hâte

0.45

 amarilla

0.41

 Entste

0.40

 copertura

0.39

 Eigentü

0.39

 חיצוניים

0.38

 nawr

0.37

 particuliers

0.37

 incidencia

0.36

Activations Density 0.001%

references to variables or parameters in mathematical expressions

No Comments

No Known Activations