INDEX

Explanations

segments of code or functions related to specific operations and parameters in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

GraphicsUnit

-0.63

ٰ

-0.61

epam

-0.57

帖最后由

-0.57

jewództ

-0.56

 Strath

-0.55

oredCriteria

-0.55

-0.54

ValueStyle

-0.54

 Cleo

-0.54

POSITIVE LOGITS

PYX

0.70

UnknownFieldSet

0.69

 original

0.63

0.62

 invokingState

0.61

TAIN

0.60

taglio

0.58

tibus

0.58

setViewportView

0.58

 contextLoads

0.57

Activations Density 0.162%

segments of code or functions related to specific operations and parameters in programming

No Comments

No Known Activations