INDEX

Explanations

terms related to patent applications and technical descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ivelany

-0.57

 organisers

-0.54

 AssemblyProduct

-0.53

 MonoBehaviour

-0.53

 Massive

-0.51

 dampen

-0.50

ReusableCell

-0.49

KommentareTeilen

-0.49

TagMode

-0.49

 budgeting

-0.49

POSITIVE LOGITS

 patent

0.69

 Patent

0.69

 INVENTION

0.62

 inventor

0.60

 patents

0.59

Patent

0.59

 onAnimation

0.59

 PATENT

0.58

bufio

0.58

patent

0.56

Activations Density 0.489%

terms related to patent applications and technical descriptions

No Comments

No Known Activations