INDEX

Explanations

proper nouns related to individuals and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

bitField

-0.84

 ioutil

-0.74

 blad

-0.74

Efe

-0.72

Andi

-0.71

ppas

-0.68

Didier

-0.67

ubourg

-0.67

Alf

-0.66

 Couch

-0.66

POSITIVE LOGITS

PrototypeOf

0.90

 Tare

0.87

 Baños

0.87

 Gira

0.85

Tow

0.84

SuppressLint

0.80

 Towne

0.80

 Baja

0.78

 flèche

0.78

meln

0.78

Activations Density 2.758%

proper nouns related to individuals and locations

No Comments

No Known Activations