INDEX

Explanations

phrases indicating exclusivity or limitation

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

only or just

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

AddTagHelper

-0.56

ContentAsync

-0.56

 noqa

-0.53

 autorytatywna

-0.52

 ProtoMessage

-0.50

 hairdryer

-0.49

 متحده

-0.47

/***/

-0.47

 AssemblyTitle

-0.46

RTCK

-0.46

POSITIVE LOGITS

 yumu

0.42

UseVisualStyle

0.39

ControllerTest

0.38

MC

0.37

 Preguntas

0.37

UnifiedTopology

0.37

 diku

0.36

kennt

0.35

↵↵

0.35

 lägga

0.35

Activations Density 0.020%

phrases indicating exclusivity or limitation

only or just

No Comments

No Known Activations