INDEX

Explanations

features related to convenience and maintainability in products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

tagHelperRunner

-0.84

<?

-0.81

 Monfieur

-0.65

 fairest

-0.62

 disambiguazione

-0.61

 Jurí

-0.60

 createState

-0.60

 germination

-0.58

CloseOperation

-0.56

 chrétiens

-0.56

POSITIVE LOGITS

 easily

0.78

 easy

0.74

 mudah

0.73

 Easily

0.68

 Easy

0.66

 modular

0.65

Easily

0.65

 readily

0.64

PreferredItem

0.64

easily

0.63

Activations Density 0.199%

features related to convenience and maintainability in products

No Comments

No Known Activations