INDEX

Explanations

technical terms related to programming and numerical operations

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

Tokens followed by "max" and its variants

np_acts-logits-general · gemini-2.0-flash

maximum or max

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 younger

-0.46

 Bryan

-0.44

-0.42

biet

-0.42

kom

-0.41

 disciple

-0.41

 Fenton

-0.39

 Christopher

-0.39

UNDER

-0.39

 nito

-0.39

POSITIVE LOGITS

max

2.06

max

2.01

 maximum

1.83

MAX

1.78

MAX

1.77

Max

1.75

Max

1.72

maximum

1.70

 Maximum

1.64

Maximum

1.64

Activations Density 0.127%

technical terms related to programming and numerical operations

Tokens followed by "max" and its variants

maximum or max

No Comments

No Known Activations