INDEX

Explanations

structured data and syntax used in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 désolés

-0.61

ANTLR

-0.61

Unmarshaller

-0.61

 незавершена

-0.58

__);

-0.58

 AssemblyCompany

-0.57

=?";

-0.57

Lähteet

-0.56

__":

-0.54

TabIndex

-0.53

POSITIVE LOGITS

 sonre

0.56

webElementGuid

0.53

 disambiguazione

0.52

BagLayout

0.52

ISupport

0.51

ionized

0.50

 Wasserstoff

0.48

EndContext

0.46

expandindo

0.46

Aged

0.45

Activations Density 0.858%

structured data and syntax used in programming code

No Comments

No Known Activations