INDEX

Explanations

programming functions and API-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RegressionTest

-0.76

findpost

-0.66

tagHelperRunner

-0.65

 Roskov

-0.62

TypedDataSet

-0.62

 ब्रेकडाउन

-0.61

-------------</

-0.60

Personendaten

-0.57

 resourceCulture

-0.56

yarnpkg

-0.55

POSITIVE LOGITS

yield

0.41

 dintre

0.40

lawayo

0.37

 Dundee

0.37

zumaki

0.35

 Duluth

0.35

XCTAssertEqual

0.35

asList

0.34

 exemple

0.33

ign

0.33

Activations Density 0.232%

programming functions and API-related terms

No Comments

No Known Activations