INDEX

Explanations

proper nouns and specific terms related to people or entities

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

Not in Any Lists

No Comments

Negative Logits

-0.74

-0.67

in

-0.57

-0.56

the

-0.56

-0.54

 BoxFit

-0.54

POSITIVE LOGITS

ArrowToggle

1.04

 Италијани

1.03

 feroit

1.00

 Italijanski

0.98

 auroit

0.95

 estimés

0.93

 étoient

0.90

NameInMap

0.89

 disambiguazione

0.89

 pouvoit

0.88

Activations Density 25.733%

proper nouns and specific terms related to people or entities

No Comments

No Known Activations