INDEX

Explanations

references to validation functions and file extensions

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

near "list" or related to file types

np_acts-logits-general · gemini-2.0-flash

valid file extensions

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

awaiter

-0.61

parsedMessage

-0.55

Alike

-0.52

findpost

-0.52

 StatelessWidget

-0.51

].(

-0.50

/**

-0.50

 cliff

-0.49

vig

-0.48

uteri

-0.48

POSITIVE LOGITS

 list

1.23

list

1.00

 List

0.97

 liste

0.96

 lista

0.92

 lists

0.91

 lijst

0.89

 listes

0.88

 LIST

0.88

ManyToMany

0.87

Activations Density 0.696%

references to validation functions and file extensions

near "list" or related to file types

valid file extensions

No Comments

No Known Activations