INDEX

Explanations

references to dates and specific temporal markers

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

dates and ranges

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

 Numerade

-0.60

 الرياضيه

-0.59

Cyfarwyddwr

-0.56

énario

-0.50

extField

-0.50

 esternos

-0.49

Fod

-0.48

ragalactic

-0.48

Newswire

-0.48

جوايز

-0.48

POSITIVE LOGITS

NameInMap

0.37

willigung

0.35

 consulte

0.35

ScopeManager

0.32

 Decke

0.31

ppur

0.31

kons

0.30

 impactos

0.30

HomeAsUpEnabled

0.29

 convierten

0.29

Activations Density 0.029%

references to dates and specific temporal markers

dates and ranges

No Comments

No Known Activations