INDEX

Explanations

terms associated with connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 leçons

-0.58

 leçon

-0.54

 preghi

-0.53

 sinais

-0.52

 preuves

-0.48

 preghiera

-0.48

algo

-0.48

 preuve

-0.47

 dentelle

-0.47

form

-0.47

POSITIVE LOGITS

tagHelperRunner

1.11

 autorytatywna

0.94

ImageContext

0.91

 related

0.85

 ProtoMessage

0.85

jspx

0.85

endphp

0.84

存于互联网档案馆

0.82

 relates

0.81

rungsseite

0.81

Activations Density 0.513%

terms associated with connections or relationships

No Comments

No Known Activations