INDEX

Explanations

mathematical notation and terms related to statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

<eos>

-1.03

↵↵

-1.01

-0.85

-0.84

-0.75

-0.73

-0.71

↵

-0.68

end

-0.67

-0.64

POSITIVE LOGITS

 myſelf

1.54

 itſelf

1.50

Efq

1.44

 pleaſure

1.42

ſelf

1.39

 purpoſe

1.39

 Jefus

1.35

 houſe

1.31

 Reſ

1.29

 Monfieur

1.29

Activations Density 2.603%

mathematical notation and terms related to statistical models

No Comments

No Known Activations