INDEX

Explanations

terminology related to software features and functionalities

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

 كومونز

-0.80

 שוליים

-0.74

AsUp

-0.72

المناصب

-0.66

 AssemblyTitle

-0.66

transQ

-0.65

setVerticalGroup

-0.63

 jLabel

-0.62

مراجع

-0.61

contentLoaded

-0.60

POSITIVE LOGITS

 feature

0.65

 capability

0.64

 section

0.60

 capabilities

0.59

 functionality

0.58

 sección

0.56

 Section

0.56

 sezione

0.56

 mechanism

0.55

GetMapping

0.53

Activations Density 0.357%

terminology related to software features and functionalities

No Comments

No Known Activations