INDEX

Explanations

nouns associated with various categories and domains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.88

 محفوظة

-0.75

Hentet

-0.73

 ivelany

-0.71

 ProtoMessage

-0.70

 Normdatei

-0.69

 Numerade

-0.69

retario

-0.67

InjectAttribute

-0.62

Portale

-0.61

POSITIVE LOGITS

/@

0.61

/…

0.56

etc

0.56

etc

0.56

jupiter

0.52

πως

0.52

0.51

/"

0.49

DONE

0.47

 durum

0.47

Activations Density 0.452%

nouns associated with various categories and domains

No Comments

No Known Activations