INDEX

Explanations

mathematical notations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

DockStyle

-0.90

parsedMessage

-0.80

DeleteBehavior

-0.80

StoryboardSegue

-0.79

UnknownFields

-0.76

 AssemblyVersion

-0.76

 AssemblyTitle

-0.75

webElement

-0.75

qrstuvwxyz

-0.74

GEBURTSDATUM

-0.72

POSITIVE LOGITS

 saja

0.49

øse

0.47

ніципа

0.46

 Estoy

0.46

lø

0.44

 maupun

0.43

mstyle

0.42

[],

0.42

0.41

 murale

0.41

Activations Density 0.617%

mathematical notations and expressions

No Comments

No Known Activations