INDEX

Explanations

terms related to data transformation and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SequentialGroup

-0.92

 picioare

-0.81

 IUPAC

-0.80

 polaire

-0.78

 Intere

-0.77

eynman

-0.77

 larmes

-0.76

 ControllerBase

-0.75

-0.74

IBarButtonItem

-0.74

POSITIVE LOGITS

 transformations

1.51

 transformation

1.50

 transforma

1.49

 transform

1.48

 transforms

1.42

 Transformations

1.40

TRANSFORM

1.35

transform

1.34

 transforming

1.33

 Transformation

1.33

Activations Density 0.110%

terms related to data transformation and processing

No Comments

No Known Activations