INDEX

Explanations

technical terms and structures related to network management and architecture

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

after "Each"

np_acts-logits-general · gemini-2.0-flash

each corresponds to a

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

 second

-0.58

cedo

-0.53

second

-0.50

 forced

-0.48

 keter

-0.47

 third

-0.46

PLICATIONS

-0.46

 hacerlo

-0.46

 caveat

-0.46

原地

-0.45

POSITIVE LOGITS

MemoryWarning

0.75

 beginnetje

0.68

tagHelperRunner

0.68

 singolo

0.66

 doInBackground

0.66

 Chaque

0.66

Chaque

0.65

withIdentifier

0.64

]")]

0.64

 identifiés

0.64

Activations Density 0.737%

technical terms and structures related to network management and architecture

after "Each"

each corresponds to a

No Comments

No Known Activations