INDEX

Explanations

references to organized groups and their classifications

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

referring to specific groups or kinds

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

domada

-0.47

-0.46

 кло

-0.41

BrowserModule

-0.39

 compens

-0.39

 كومونز

-0.38

 prome

-0.38

Alexander

-0.36

 rând

-0.36

Conditional

-0.36

POSITIVE LOGITS

 disambiguazione

0.54

IUrlHelper

0.52

بوابة

0.50

BeginContext

0.47

ніципалі

0.47

 ostavi

0.44

 onCreateView

0.44

 ProtoMessage

0.43

:✨

0.43

Portale

0.43

Activations Density 0.064%

references to organized groups and their classifications

referring to specific groups or kinds

No Comments

No Known Activations