INDEX

Explanations

terminology and definitions related to processes and systems in technical contexts

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

introducing a definition or name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

($)

-0.45

⅘

-0.43

fVar

-0.43

pleen

-0.41

ervlak

-0.40

tzmann

-0.39

 negotiator

-0.39

جمعیت

-0.38

 Apes

-0.38

 wasn

-0.38

POSITIVE LOGITS

NameInMap

0.63

 <=",

0.52

called

0.52

 disambiguazione

0.49

цездатний

0.47

يميديا

0.47

 chamado

0.47

ніципалі

0.46

 propOrder

0.46

 called

0.45

Activations Density 0.069%

terminology and definitions related to processes and systems in technical contexts

introducing a definition or name

No Comments

No Known Activations