INDEX

Explanations

occurrences of significant legal and regulatory terms

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

motion vector; foreign words

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

 EconPapers

-0.57

 Wikimedijinoj

-0.55

expandindo

-0.54

 ProtoMessage

-0.53

Scénario

-0.53

 nahilalakip

-0.53

 Italijanski

-0.52

 estekak

-0.51

出版年

-0.50

 surla

-0.50

POSITIVE LOGITS

 IndexError

0.41

 varandra

0.36

 einz

0.36

ClientSize

0.35

 verein

0.35

wier

0.35

 dzisiaj

0.34

 säkert

0.34

 bezpeč

0.33

jej

0.33

Activations Density 0.099%

occurrences of significant legal and regulatory terms

motion vector; foreign words

No Comments

No Known Activations