INDEX

Explanations

phrases related to programming concepts, specifically focusing on synchronization and concurrency in code execution

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

"increase" or "increment"

np_acts-logits-general · gemini-2.0-flash

unit increase

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Marry

-0.48

interopRequire

-0.44

ablon

-0.43

 cavo

-0.42

ấu

-0.42

 resemblance

-0.41

 early

-0.39

 späteren

-0.39

zwe

-0.39

 Optimal

-0.39

POSITIVE LOGITS

 increase

1.66

increase

1.56

Increase

1.49

 Increase

1.48

 increment

1.42

 increases

1.39

 INCREASE

1.33

increment

1.32

 incre

1.26

 increased

1.26

Activations Density 0.447%

phrases related to programming concepts, specifically focusing on synchronization and concurrency in code execution

"increase" or "increment"

unit increase

No Comments

No Known Activations