INDEX

Explanations

phrases related to feedback, requests for help, and guidance

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

starting with "disper", "proces", or "apps"

np_acts-logits-general · gemini-2.0-flash

dispersion, processivity, appsensor

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 movement

-0.62

за

-0.50

 Movement

-0.50

Movement

-0.49

zer

-0.48

これで

-0.48

zu

-0.46

za

-0.46

ze

-0.46

зами

-0.44

POSITIVE LOGITS

FailureListener

0.83

 مشين

0.80

 propOrder

0.78

UserScript

0.77

ioutil

0.67

addCriterion

0.66

 AssemblyTitle

0.66

ModelBuilder

0.66

atrician

0.65

GrantedAuthority

0.64

Activations Density 0.120%

phrases related to feedback, requests for help, and guidance

starting with "disper", "proces", or "apps"

dispersion, processivity, appsensor

No Comments

No Known Activations

phrases related to feedback, requests for help, and guidance

starting with "disper", "proces", or "apps"

dispersion, processivity, appsensor

No Comments

No Known Activations