INDEX

Explanations

punctuation or comment indicators in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 propOrder

-0.63

 Administrativna

-0.61

enumii

-0.52

 autorytatywna

-0.50

Autoritní

-0.49

ActionCreators

-0.47

 ſche

-0.46

Nul

-0.46

 Савезне

-0.46

 mapStateToProps

-0.46

POSITIVE LOGITS

 Erkenntnis

0.40

onViewCreated

0.40

 Hinweis

0.39

 París

0.38

liefert

0.38

 zufolge

0.37

 aplicable

0.37

Atentamente

0.37

 alemana

0.36

 scolaires

0.36

Activations Density 0.000%

punctuation or comment indicators in code

No Comments

No Known Activations