INDEX

Explanations

references to upcoming events and recent occurrences

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

recent and upcoming events

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

 nakalista

-0.60

SEGUIR

-0.56

 betweenstory

-0.52

 auroit

-0.52

 pouvoit

-0.51

IBarButtonItem

-0.51

SourceChecksum

-0.50

 raiſ

-0.50

 Juifs

-0.49

Reprodução

-0.49

POSITIVE LOGITS

 upcoming

0.59

 recent

0.59

 ongoing

0.49

 major

0.48

upcoming

0.45

 joint

0.45

 recente

0.45

 useSelector

0.43

 forthcoming

0.43

 previous

0.43

Activations Density 0.021%

references to upcoming events and recent occurrences

recent and upcoming events

No Comments

No Known Activations