INDEX

Explanations

references to a specific bootstrap procedure or method

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

bootstrap particle filter

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

[]:

-0.45

 InputDecoration

-0.45

 nakalista

-0.42

spells

-0.39

WireFormat

-0.39

 Enviar

-0.38

PMailer

-0.38

RTLU

-0.38

énario

-0.37

ragalactic

-0.37

POSITIVE LOGITS

 bootstrap

0.88

 Bootstrap

0.87

 bootstra

0.81

Bootstrap

0.78

bootstrap

0.73

 Boot

0.72

 BOOT

0.70

BOOT

0.69

 boot

0.68

Boot

0.65

Activations Density 0.004%

references to a specific bootstrap procedure or method

bootstrap particle filter

No Comments

No Known Activations