INDEX

Explanations

technical terminology related to electrical engineering and computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 <<<<<<<<<<<<<<

-0.61

 endblock

-0.57

')}}">

-0.53

esinde

-0.51

Carriera

-0.50

 autorytatywna

-0.49

 }}"></

-0.49

"])

-0.49

meneu

-0.48

 MessageType

-0.47

POSITIVE LOGITS

 BoxFit

0.56

 fermée

0.54

 hänen

0.54

 braccio

0.53

 correctes

0.52

jame

0.51

bonucleic

0.51

 réservé

0.50

 FetchType

0.49

 imprimée

0.49

Activations Density 1.022%

technical terminology related to electrical engineering and computing

No Comments

No Known Activations