INDEX

Explanations

terms related to parity in mathematical or physical contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

parity and disparity

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

Negative Logits

Wass

-0.41

Spoon

-0.40

Instrument

-0.40

TCS

-0.37

spoon

-0.36

 tucson

-0.36

 Wund

-0.36

 Spoon

-0.35

 tremb

-0.35

Google

-0.34

POSITIVE LOGITS

 parity

2.97

 Parity

2.73

parity

2.53

Parity

2.48

 disparity

1.04

 parody

0.95

 equality

0.91

 disparities

0.79

 Parry

0.78

arity

0.74

Activations Density 0.006%

terms related to parity in mathematical or physical contexts

parity and disparity

No Known Activations