INDEX

Explanations

references to recent developments or noteworthy changes in various contexts

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

significant changes and developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

SourceChecksum

-0.31

 compagnon

-0.30

 Mittelpunkt

-0.29

 Dreh

-0.28

andu

-0.27

 existing

-0.27

 horaire

-0.27

 budu

-0.27

 istnie

-0.27

Existing

-0.27

POSITIVE LOGITS

 resurgence

0.99

 renaissance

0.98

 surge

0.93

 wave

0.92

 flurry

0.90

 explosion

0.89

 boom

0.88

 onslaught

0.86

 exodus

0.84

explosion

0.82

Activations Density 0.062%

references to recent developments or noteworthy changes in various contexts

significant changes and developments

No Comments

No Known Activations