INDEX

Explanations

sections that denote the beginning of a new topic or paragraph

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

featureID

-0.69

SuppressMessage

-0.68

Personendaten

-0.67

ISupport

-0.65

__*/

-0.62

transQ

-0.60

RuleContext

-0.57

IsInitialized

-0.56

 vuitton

-0.55

offerta

-0.54

POSITIVE LOGITS

expandindo

0.65

 مرئيه

0.64

Tikang

0.57

 estimés

0.55

webElementGuid

0.55

 iconFacebook

0.52

 Infórmanos

0.49

 оригіналу

0.47

 Перейти

0.46

Activations Density 0.014%

sections that denote the beginning of a new topic or paragraph

No Comments

No Known Activations