INDEX

Explanations

terminology and references related to discussions and dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

•Cluster 31

No Comments

Negative Logits

 lievito

-0.57

 mệnh

-0.55

 собой

-0.49

 Borden

-0.49

 määrä

-0.47

τως

-0.47

やかに

-0.46

 Enfield

-0.46

 useAuth

-0.46

baceous

-0.46

POSITIVE LOGITS

Vidite

0.85

 betweenstory

0.81

 topics

0.78

 transfieras

0.78

hicles

0.72

 utafitiHapana

0.72

 topic

0.67

verwijspagina

0.67

 sumpay

0.67

Topics

0.65

Activations Density 0.146%

terminology and references related to discussions and dialogue

No Comments

No Known Activations