INDEX

Explanations

references to planning and scheduling activities

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

plans and alibis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

InitVars

-0.42

ViewImports

-0.37

 Recurrent

-0.35

IsMutable

-0.35

EndContext

-0.34

///</

-0.34

</tfoot>

-0.34

ApiModelProperty

-0.32

/*

-0.32

 nakalista

-0.32

POSITIVE LOGITS

 alibi

0.66

WaitGroup

0.57

 lunch

0.54

inerary

0.53

 whereabouts

0.52

plans

0.51

 Itinerary

0.51

 itinerary

0.51

 plans

0.50

Lunch

0.50

Activations Density 0.166%

references to planning and scheduling activities

plans and alibis

No Comments

No Known Activations