INDEX

Explanations

references to Lorentz transformations and violations associated with physical theories

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

Lorentz symmetry

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

ioutil

-0.37

Papier

-0.37

 assail

-0.36

 obsequ

-0.36

 vole

-0.36

池

-0.35

池

-0.35

TaskId

-0.35

 ananas

-0.35

Bob

-0.35

POSITIVE LOGITS

 Lorenz

1.25

 Lorentz

1.20

Loren

1.08

 loren

1.05

 Loren

1.05

 Lorenzo

0.90

WRENCE

0.87

 Laurent

0.85

LOR

0.84

 Laurence

0.83

Activations Density 0.020%

references to Lorentz transformations and violations associated with physical theories

Lorentz symmetry

No Comments

No Known Activations