INDEX

Explanations

various types of numerical values and references that suggest metrics or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 three

-0.63

 third

-0.56

 }^{(

-0.55

 Desa

-0.54

 Third

-0.54

 Three

-0.53

zmán

-0.49

 August

-0.48

 fourth

-0.47

ttino

-0.47

POSITIVE LOGITS

1.55

yntaxException

0.72

六

0.70

0.63

 Réponses

0.62

六

0.61

 Sixth

0.59

VI

0.58

VI

0.57

Activations Density 0.158%

various types of numerical values and references that suggest metrics or measurements

No Comments

No Known Activations