INDEX

Explanations

elements related to data structures and their manipulations

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

Code delimiters and punctuation

np_acts-logits-general · gemini-2.0-flash

numerals and punctuation

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

 للمعارف

-0.88

SourceChecksum

-0.86

########.

-0.82

afficheront

-0.79

Hentet

-0.78

APORE

-0.78

 الحره

-0.77

ритори

-0.77

发表于

-0.76

ioutil

-0.75

POSITIVE LOGITS

 Theſe

0.55

 Monfieur

0.52

 auroit

0.47

 étoit

0.45

 feroit

0.44

 myſelf

0.44

 pouvoit

0.43

<bos>

0.41

 mourut

0.38

 himſelf

0.38

Activations Density 0.300%

elements related to data structures and their manipulations

Code delimiters and punctuation

numerals and punctuation

No Comments

No Known Activations