INDEX

Explanations

references to programming terminology and structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 marquées

-0.59

 CURLOPT

-0.57

ChildScrollView

-0.52

/}.

-0.52

 Hiros

-0.50

Whole

-0.50

 CommandType

-0.50

مراجع

-0.49

whole

-0.49

ThroughAttribute

-0.49

POSITIVE LOGITS

webElementXpaths

0.56

awaiter

0.56

цездатний

0.55

ViewImports

0.54

VIAF

0.53

يكب

0.52

:✨

0.49

SourceChecksum

0.49

SceneManagement

0.49

bonucle

0.49

Activations Density 0.099%

references to programming terminology and structures

No Comments

No Known Activations