INDEX

Explanations

code snippets and structures related to testing and assertions 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.53

 répondit

-0.52

wpi

-0.52

 obicei

-0.51

DrawerToggle

-0.50

formik

-0.49

basicConfig

-0.47

("~/

-0.47

GraphicsUnit

-0.47

toPromise

-0.47

POSITIVE LOGITS

 tests

0.76

RegressionTest

0.69

 tested

0.66

testng

0.66

 tester

0.64

 test

0.64

 cases

0.63

 TESTS

0.62

Tests

0.62

 illustrative

0.61

Activations Density 0.255%

code snippets and structures related to testing and assertions in programming

No Comments

No Known Activations