INDEX

Explanations

proper nouns and names associated with people and places

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

Lip

-0.81

Lip

-0.74

MOT

-0.73

lip

-0.72

 Lips

-0.66

LIP

-0.65

Zag

-0.63

Tas

-0.63

Zag

-0.62

 Beard

-0.62

POSITIVE LOGITS

 Golem

0.90

GEBURTSDATUM

0.88

 humer

0.87

Према

0.86

 Lenti

0.85

 Malte

0.85

 Wiktionnaire

0.84

 Biotechnol

0.82

Nintendo

0.82

 Mitter

0.82

Activations Density 1.369%

proper nouns and names associated with people and places

No Comments

No Known Activations