INDEX

Explanations

specific player performance metrics in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 στρα

-0.39

CppCodeGen

-0.39

 HttpNotFound

-0.38



-0.38

//

-0.37

createServer

-0.37

fjspx

-0.37

 policing

-0.35

itsi

-0.35

 package

-0.35

POSITIVE LOGITS

 hitters

0.75

 hitter

0.71

 batters

0.70

 batting

0.68

 batter

0.63

 hitting

0.63

 batsman

0.60

Hit

0.57

bat

0.57

 strike

0.57

Activations Density 0.064%

specific player performance metrics in a sports context

No Comments

No Known Activations