INDEX

Explanations

occurrences of user-related functionality in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

@"/

-0.60

Cyfeiriadau

-0.56

 تعدى

-0.55

webElementXpaths

-0.54

Revenir

-0.53

devamını

-0.52

resizingMask

-0.51

CodeAnalysis

-0.50

Hochspringen

-0.50

komt

-0.49

POSITIVE LOGITS

 дописавши

0.80

 للاسماء

0.71

)";

0.70

 الاطلاع

0.62

DeleteBehavior

0.61

 AssemblyProduct

0.59

PARATOR

0.57

!")

0.57

UnknownFieldSet

0.57

^(@)

0.57

Activations Density 0.123%

occurrences of user-related functionality in code

No Comments

No Known Activations