INDEX

Explanations

references to a character named Champ

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

Champ, champs, Champlain

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

VIAF

-0.46

///

-0.44

 currentNode

-0.38

autorest

-0.38

.}\

-0.37

 VIAF

-0.37

::$_

-0.36

VSS

-0.35

"}},

-0.35

 Grig

-0.35

POSITIVE LOGITS

 Champ

2.45

Champ

2.41

 champ

2.23

champ

2.22

 CHAMP

1.90

 champs

1.88

 Champs

1.86

CHAMP

1.62

champs

1.62

 CHAM

1.44

Activations Density 0.003%

references to a character named Champ

Champ, champs, Champlain

No Comments

No Known Activations