INDEX

Explanations

personal interactions and experiences involving the self

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

First-person pronouns and possessives

np_acts-logits-general · gemini-2.0-flash

first-person perspective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gameserver

-0.48

Pranala

-0.47

 habet

-0.41

ois

-0.39

urfs

-0.39

 deleteById

-0.38

bpy

-0.38

 HomeController

-0.38

cir

-0.38

 facult

-0.38

POSITIVE LOGITS

GOTREF

0.62

 myself

0.55

 '\\;'

0.52

enterOuterAlt

0.50

новниш

0.50

addContainerGap

0.46

 unknownFields

0.42

IntoConstraints

0.42

 հղումներ

0.42

SharedDtor

0.42

Activations Density 0.347%

personal interactions and experiences involving the self

First-person pronouns and possessives

first-person perspective

No Comments

No Known Activations