INDEX

Explanations

comments and documentation in code

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

Code comments and license headers

np_acts-logits-general · gemini-2.0-flash

distributed license text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

ckså

-0.45

 mijne

-0.44

viewtopic

-0.40

 ashamed

-0.40

 clicar

-0.39

 muur

-0.38

seamnă

-0.38

แห

-0.38

 wireType

-0.37

miyorum

-0.37

POSITIVE LOGITS

########.

0.53

WebElementEntity

0.50

 otomatig

0.48

SBATCH

0.47

ngrx

0.45

xnn

0.44

__;

0.43

 surla

0.42

:✨

0.41

RTHOOK

0.41

Activations Density 0.264%

comments and documentation in code

Code comments and license headers

distributed license text

No Comments

No Known Activations

comments and documentation in code

Code comments and license headers

distributed license text

No Comments

No Known Activations