INDEX

Explanations

terms related to historical figures and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 للمعارف

-0.53

 đầu

-0.51

 rato

-0.48

eably

-0.46

 under

-0.46

 post

-0.46

Personensuche

-0.45

 مقابل

-0.45

 status

-0.44

dom

-0.44

POSITIVE LOGITS

IntoConstraints

0.80

 itſelf

0.77

 invokingState

0.75

 surla

0.67

 myſelf

0.65

 CURIAM

0.60

 chrétienne

0.59

PreferredItem

0.59

 Besoin

0.58

 iſt

0.58

Activations Density 0.358%

terms related to historical figures and locations

No Comments

No Known Activations