INDEX

Explanations

names of notable individuals associated with specific accomplishments or historical events

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

names followed by common words

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

ActionCreators

-0.70

+#+#

-0.66

TypedDataSet

-0.64

 للمعارف

-0.60

RegistryLite

-0.60

 surla

-0.59

 intptr

-0.57

apimachinery

-0.57

ftagPool

-0.57

EndContext

-0.56

POSITIVE LOGITS

bootstrapcdn

0.46

Демографія

0.43

 later

0.40

клопе

0.39

 young

0.38

 futura

0.37

young

0.36

 initially

0.36

 kés

0.36

 découv

0.35

Activations Density 0.050%

names of notable individuals associated with specific accomplishments or historical events

names followed by common words

No Comments

No Known Activations