INDEX

Explanations

mathematical expressions and symbols related to functions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

blage

-0.49

KURZBESCHREIBUNG

-0.48

exitRule

-0.48

 endblock

-0.47

Lycka

-0.41

inWeight

-0.41

 rhestr

-0.40

 يتيمه

-0.39

 kiin

-0.39

 propOrder

-0.39

POSITIVE LOGITS

 expon

0.51

NOPQRST

0.47

FlatAppearance

0.44

INFL

0.41

 GetEnumerator

0.41

acc

0.39

 expansion

0.38

Ehrungen

0.38

 power

0.37

 expansions

0.37

Activations Density 1.250%

mathematical expressions and symbols related to functions and equations

No Comments

No Known Activations