INDEX

Explanations

references to participants in a game or sport

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

players and their actions

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

six

-0.49

 dimenti

-0.47

PostConstruct

-0.42

 Wain

-0.42

 Cuth

-0.41

to

-0.41

 RECENT

-0.41

 sixth

-0.40

 Neuf

-0.40

Bif

-0.40

POSITIVE LOGITS

 Players

1.48

Players

1.45

players

1.44

 getPlayer

1.41

 players

1.38

 Player

1.36

Player

1.35

 player

1.32

player

1.29

 PLAYER

1.24

Activations Density 0.013%

references to participants in a game or sport

players and their actions

No Comments

No Known Activations