INDEX

Explanations

specific references and mentions related to diverse topics or entities

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

followed by "and"

np_acts-logits-general · gemini-2.0-flash

the word and

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 nonUne

-0.56

BASELINE

-0.54

 Superhosts

-0.53

getDoctrine

-0.52

 vettoriale

-0.51

stateProvider

-0.50

parsedMessage

-0.48

clyde

-0.48

 okuyayım

-0.46

 needs

-0.45

POSITIVE LOGITS

 others

0.46

others

0.45

 linkovi

0.44

possibly

0.40

recently

0.39

NameInMap

0.39

__;

0.38

GeneratedCode

0.37

occas

0.36

 мәкал

0.35

Activations Density 0.469%

specific references and mentions related to diverse topics or entities

followed by "and"

the word and

No Comments

No Known Activations