INDEX

Explanations

references to patents and patent applications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MonoBehaviour

-0.54

ReusableCell

-0.53

шками

-0.52

matchCondition

-0.51

 AssemblyTitle

-0.50

WithMany

-0.50

ISupport

-0.50

__*/

-0.49

 escor

-0.48

 evacu

-0.48

POSITIVE LOGITS

 patent

0.87

 Patent

0.82

Patent

0.75

 PATENT

0.72

 patents

0.70

patent

0.70

 Patents

0.69

mbggenerated

0.67

 onAnimation

0.62

ArrowToggle

0.61

Activations Density 0.420%

references to patents and patent applications

No Comments

No Known Activations