INDEX

Explanations

positive descriptions and compliments related to images or posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

kuuta

-0.58

MongoClient

-0.56

askar

-0.55

 hObject

-0.52

timewa

-0.51

jenner

-0.51

 resolução

-0.50

 peggio

-0.49

iego

-0.49

UGHS

-0.48

POSITIVE LOGITS

//

0.75

 Drapeau

0.57

GNP

0.56

ngdoc

0.54

XmlAccessorType

0.54

Où

0.52

OGND

0.52

Outstanding

0.51

caught

0.51

 organics

0.50

Activations Density 0.134%

positive descriptions and compliments related to images or posts

No Comments

No Known Activations