INDEX

Explanations

numerical values and code references

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

scientific measurement objectives

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

ScopeManager

-0.65

 referrerpolicy

-0.60

 Paglinawan

-0.57

ंदीखरीदारी

-0.57

Personensuche

-0.57

qtype

-0.56

 AssemblyCulture

-0.56

 Numerade

-0.53

NameInMap

-0.53

+#+#

-0.52

POSITIVE LOGITS

unnitel

0.44

 Krü

0.40

further

0.39

 razonable

0.36

 ladrillo

0.36

 olev

0.36

 Petrov

0.36

 élevé

0.36

 asti

0.36

 tĩnh

0.35

Activations Density 0.002%

numerical values and code references

scientific measurement objectives

No Comments

No Known Activations