INDEX

Explanations

connections between topics or entities in a text

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

connected to other words

np_acts-logits-general · gemini-2.0-flash

relationships and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

principalTable

-0.33

สะ

-0.33

정

-0.31

Repositorio

-0.30

 محفوظة

-0.30

 aanv

-0.30

ptos

-0.29

 Entsch

-0.29

 composta

-0.29

cellent

-0.29

POSITIVE LOGITS

 OFDb

0.56

 politics

0.55

 illness

0.53

 criminality

0.53

 sexuality

0.53

ValueStyle

0.53

ObjectContext

0.52

 terrorism

0.51

深い

0.51

AttributeName

0.50

Activations Density 0.651%

connections between topics or entities in a text

connected to other words

relationships and associations

No Comments

No Known Activations