INDEX

Explanations

references to test cases and testing frameworks in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Meksiku

-0.67

PYX

-0.55

 Ause

-0.53

Initializable

-0.50

 campan

-0.45

chere

-0.43

なもの

-0.43

 cruzado

-0.43

вказ

-0.43

 uVar

-0.43

POSITIVE LOGITS

Test

2.34

 Test

2.09

TestMethod

1.71

TEST

1.50

test

1.49

 TEST

1.43

 test

1.40

 Tests

1.38

ServiceTest

1.33

ControllerTest

1.21

Activations Density 0.094%

references to test cases and testing frameworks in code

No Comments

No Known Activations