INDEX

Explanations

information related to invention and patenting processes

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

ENOMEM

-0.64

клопе

-0.60

 auffi

-0.59

 MainAxisSize

-0.57

 لينك

-0.55

IsContent

-0.55

 MonoBehaviour

-0.54

 الرياضيه

-0.53



-0.53

 يتيمه

-0.51

POSITIVE LOGITS

 patent

2.00

 patents

1.85

 Patent

1.76

patent

1.69

 intellectual

1.67

 Intellectual

1.60

 copyright

1.59

 Patents

1.58

Patent

1.56

 trademark

1.52

Activations Density 0.872%

information related to invention and patenting processes

No Comments

No Known Activations