INDEX

Explanations

references to class definitions 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

bootstrapcdn

-0.70

 MainAxisSize

-0.67

клопе

-0.54

 beträ

-0.53

thschild

-0.51

 незавершена

-0.51

หว่าง

-0.50

 aikana

-0.49

families

-0.48

gruppen

-0.48

POSITIVE LOGITS

ⓧ

0.71

✨:

0.67

/*

0.65

 {}),

0.63

migrationBuilder

0.60

 continúas

0.60

tvguidetime

0.57

例文帳に追加

0.56

 Roskov

0.55

Tembelea

0.55

Activations Density 0.310%

references to class definitions in programming code

No Comments

No Known Activations