INDEX

Explanations

questions about numerical comparisons and mathematical operations

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

Question marks followed by answers

np_acts-logits-general · gemini-2.0-flash

computational entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.71

and

-0.69

-0.63

-0.56

-0.54

to

-0.53

or

-0.50

-0.49

POSITIVE LOGITS

GEBURTSDATUM

1.69

 kasarigan

1.45

TagMode

1.36

 defaultstate

1.35

 الحره

1.33

IntoConstraints

1.32

featureID

1.31



1.30

 NSCoder

1.29

 pinulongan

1.29

Activations Density 0.583%

questions about numerical comparisons and mathematical operations

Question marks followed by answers

computational entities

No Comments

No Known Activations