INDEX

Explanations

terms related to collaboration and teamwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

fromCharCode

-0.63

balleur

-0.62

دانشنامهٔ

-0.58

脚注の使い方

-0.57

Gweler

-0.56

 majorité

-0.56

 giustizia

-0.56

 nôtre

-0.56

 popoli

-0.55

 commerciaux

-0.55

POSITIVE LOGITS

lant

0.52

 hand

0.52

TableAdapter

0.50

OVA

0.49

ERI

0.49

 Biôgrafia

0.48

AspNetCore

0.48

 Bann

0.47

 Crosse

0.47

plant

0.47

Activations Density 0.121%

terms related to collaboration and teamwork

No Comments

No Known Activations