INDEX

Explanations

verbs indicating intent or desire

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

express intent to act

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

+#+

-0.53

CodedInputStream

-0.52

parsedMessage

-0.49

 viſ

-0.48

новништво

-0.47

thâu

-0.47

IndentedString

-0.47

 fubject

-0.47

envoy

-0.46

tangentMode

-0.45

POSITIVE LOGITS

 করা

0.44

jenigen

0.40

 Zeitpunkt

0.38

jenige

0.38

 tangan

0.38

 Wikiseite

0.37

 archivi

0.37

出版年

0.37

卸

0.36

 հղումներ

0.36

Activations Density 0.035%

verbs indicating intent or desire

express intent to act

No Comments

No Known Activations