INDEX

Explanations

punctuation marks and symbols indicating the end of sentences and questions

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

punctuation followed by sentence starter

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

polar

-0.43

Means

-0.42

Polar

-0.40

 चाहता

-0.38

deci

-0.38

 <<<<<<<<<<<<<<

-0.38

 EconPapers

-0.38

 Polar

-0.37

 Alloys

-0.37

 gwiazd

-0.36

POSITIVE LOGITS

PerformLayout

0.55

 noDo

0.52

hyrchwyd

0.52

 mutta

0.49

utuhkan

0.48

AndEndTag

0.47

 виправивши

0.45

rungsseite

0.45

Autoritní

0.45

 AssemblyCompany

0.44

Activations Density 0.191%

punctuation marks and symbols indicating the end of sentences and questions

punctuation followed by sentence starter

No Comments

No Known Activations