INDEX

Explanations

phrases indicating temporal relationships or events occurring after specific moments

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

common follow-ups

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

AndEndTag

-0.69

 مرئيه

-0.62

 autorytatywna

-0.60

 gynhyrchwyd

-0.57

tiérrez

-0.56

 مشين

-0.53

annica

-0.53

esgue

-0.53

 שוליים

-0.52

Personensuche

-0.52

POSITIVE LOGITS

won

0.36

ple

0.31

 writeTo

0.29

 Sante

0.28

 then

0.28

 soon

0.28

서는

0.28

 become

0.28

OpenHelper

0.28

now

0.28

Activations Density 0.030%

phrases indicating temporal relationships or events occurring after specific moments

common follow-ups

No Comments

No Known Activations