INDEX

Explanations

questions and reasons behind actions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

EndProject

-0.58

utches

-0.52

شهاد

-0.51

形で

-0.50

 resourceCulture

-0.47

 Signalez

-0.47

 mely

-0.47

Семья

-0.46

MLLoader

-0.46

TestingModule

-0.45

POSITIVE LOGITS

 because

2.20

 Because

1.99

Because

1.96

because

1.94

 porque

1.90

 BECAUSE

1.79

 потому

1.69

 Потому

1.62

Porque

1.56

 perché

1.53

Activations Density 0.296%

questions and reasons behind actions or beliefs

No Comments

No Known Activations