INDEX

Explanations

elements related to repository design patterns and abstract class definitions 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 typelib

-0.72

 ModelExpression

-0.70

+#+

-0.68

featureID

-0.66

StoryboardSegue

-0.64

 resourceCulture

-0.61

 iprot

-0.59

TestingModule

-0.54

 surla

-0.53

 *)__

-0.53

POSITIVE LOGITS

 aasta

0.63

 myſelf

0.62

 themſelves

0.60

 pleaſure

0.58

NUMX

0.58

 fubject

0.55

]='\

0.54

 aastal

0.54

 itſelf

0.53

ródło

0.52

Activations Density 0.088%

elements related to repository design patterns and abstract class definitions in programming

No Comments

No Known Activations