INDEX

Explanations

references to specific entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

GEBURTSDATUM

-0.54

 humaines

-0.54

ElementException

-0.53

 rayons

-0.52

otheses

-0.50

lemb

-0.50

IntoConstraints

-0.48

 humaine

-0.48

페

-0.46

 blame

-0.46

POSITIVE LOGITS

 propOrder

0.78

canestro

0.70

EndContext

0.68

 jScrollPane

0.67

kmäler

0.63

 protoimpl

0.63

 transférez

0.60

 Италијани

0.58

 муніципалі

0.56

 ErrIntOverflow

0.56

Activations Density 0.163%

references to specific entities or organizations

No Comments

No Known Activations