INDEX

Explanations

keywords or phrases related to data structures and programming constructs

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

دانشنامهٔ

-0.91

msgTypes

-0.86

 AssemblyCulture

-0.86

 estekak

-0.84

 للاسماء

-0.83

AndroidJUnit

-0.74

évaluateur

-0.74

SourceChecksum

-0.73

 Мексичка

-0.72

nextProps

-0.71

POSITIVE LOGITS

readObject

0.50

lements

0.46

luit

0.43

*{

0.42

ари

0.42

<u>

0.42

 concentric

0.40

anyl

0.40

 Delicious

0.38

اعي

0.37

Activations Density 0.695%

keywords or phrases related to data structures and programming constructs

No Comments

No Known Activations