INDEX

Explanations

terms related to equipment and service considerations

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

Followed by punctuation or prepositions

np_acts-logits-general · gemini-2.0-flash

listing features or types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

сылкі

-0.78

featureID

-0.61

kháu

-0.59

msgTypes

-0.59

 otomatig

-0.58

 kind

-0.54

DotNetBar

-0.53

SBATCH

-0.53

AccessorTable

-0.52

 ossia

-0.52

POSITIVE LOGITS

 correspondiente

0.54

 engraçadas

0.52

ільки

0.52

 devido

0.50

 înc

0.49

 mắn

0.48

?!

0.48

 ...)

0.48

 müm

0.48

 posteriores

0.48

Activations Density 0.139%

terms related to equipment and service considerations

Followed by punctuation or prepositions

listing features or types

No Comments

No Known Activations