INDEX

Explanations

phrases related to announcements and presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

CGRect

-0.50

ihnachten

-0.45

ihnachts

-0.45

 opérateur

-0.45

orthand

-0.43

-------

-0.42

UseVisualStyle

-0.42

 Standardized

-0.42

 intest

-0.42

 Jurí

-0.41

POSITIVE LOGITS

 AssemblyProduct

0.86

########.

0.79

Gambas

0.78

 المعيارى

0.72

 ErrIntOverflow

0.71

 ComVisible

0.70

webElementXpaths

0.69

migrationBuilder

0.69

Jeografia

0.68

MLLoader

0.68

Activations Density 0.137%

phrases related to announcements and presentations

No Comments

No Known Activations